# Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models

arXiv: https://arxiv.org/abs/2402.16438 · HTML: https://mlsanity.com/paper/2402.16438/

## Key facts

- Cited by 126 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 26 Feb 2024.

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Finding Neurons in a Haystack: Case Studies with Sparse Probing](https://mlsanity.com/paper/2305.01610/) (2023)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Cross-Lingual Ability of Multilingual BERT: An Empirical Study](https://mlsanity.com/paper/1912.07840/) (2019)
- [Emerging Cross-lingual Structure in Pretrained Language Models](https://mlsanity.com/paper/1911.01464/) (2019)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Learning to Generate Reviews and Discovering Sentiment](https://mlsanity.com/paper/1704.01444/) (2017)
- [What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models](https://mlsanity.com/paper/1812.09355/) (2018)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [Identifying and Controlling Important Neurons in Neural Machine Translation](https://mlsanity.com/paper/1811.01157/) (2018)
- [SeaLLMs -- Large Language Models for Southeast Asia](https://mlsanity.com/paper/2312.00738/) (2023)
- [Universal Neurons in GPT2 Language Models](https://mlsanity.com/paper/2401.12181/) (2024)
- [Neurons in Large Language Models: Dead, N-gram, Positional](https://mlsanity.com/paper/2309.04827/) (2023)
- [Neuron-level Interpretation of Deep NLP Models: A Survey](https://mlsanity.com/paper/2108.13138/) (2021)
- [Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlations](https://mlsanity.com/paper/1906.01181/) (2019)
- [Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons](https://mlsanity.com/paper/2308.13198/) (2023)
- [Towards a Common Understanding of Contributing Factors for Cross-Lingual Transfer in Multilingual Language Models: A Review](https://mlsanity.com/paper/2305.16768/) (2023)
- [When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer](https://mlsanity.com/paper/2110.14782/) (2021)
- [Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding](https://mlsanity.com/paper/2309.07098/) (2023)

## Built on by (most cited first, 30 of 126)

- [How do Large Language Models Handle Multilingualism?](https://mlsanity.com/paper/2402.18815/) (2024)
- [Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders](https://mlsanity.com/paper/2410.20526/) (2024)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities](https://mlsanity.com/paper/2411.04986/) (2024)
- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [Knowledge Mechanisms in Large Language Models: A Survey and Perspective](https://mlsanity.com/paper/2407.15017/) (2024)
- [Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers](https://mlsanity.com/paper/2411.08745/) (2024)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [Talking Heads: Understanding Inter-layer Communication in Transformer Language Models](https://mlsanity.com/paper/2406.09519/) (2024)
- [A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models](https://mlsanity.com/paper/2502.17516/) (2025)
- [Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs](https://mlsanity.com/paper/2406.09265/) (2024)
- [Multilingual Routing in Mixture-of-Experts](https://mlsanity.com/paper/2510.04694/) (2025)
- [The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling](https://mlsanity.com/paper/2410.09223/) (2024)
- [Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research](https://mlsanity.com/paper/2412.04497/) (2024)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model](https://mlsanity.com/paper/2406.11193/) (2024)
- [Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons](https://mlsanity.com/paper/2407.06488/) (2024)
- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (2024)
- [RepreGuard: Detecting LLM-Generated Text by Revealing Hidden Representation Patterns](https://mlsanity.com/paper/2508.13152/) (2025)
- [How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?](https://mlsanity.com/paper/2406.11477/) (2024)
- [Configurable Foundation Models: Building LLMs from a Modular Perspective](https://mlsanity.com/paper/2409.02877/) (2024)
- [Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs](https://mlsanity.com/paper/2408.10646/) (2024)
- [Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models](https://mlsanity.com/paper/2410.01335/) (2024)
- [Language-Specific Latent Process Hinders Cross-Lingual Performance](https://mlsanity.com/paper/2505.13141/) (2025)
- [Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline](https://mlsanity.com/paper/2505.20546/) (2025)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [Multilingual Knowledge Editing with Language-Agnostic Factual Neurons](https://mlsanity.com/paper/2406.16416/) (2024)
- [Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing](https://mlsanity.com/paper/2410.07054/) (2024)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment](https://mlsanity.com/paper/2501.03681/) (2025)

## Abstract (arXiv)

Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora. It remains a challenging problem to explain the underlying mechanisms by which LLMs process multilingual texts. In this paper, we delve into the composition of Transformer architectures in LLMs to pinpoint language-specific regions. Specially, we propose a novel detection method, language activation probability entropy (LAPE), to identify language-specific neurons within LLMs. Based on LAPE, we conduct comprehensive experiments on several representative LLMs, such as LLaMA-2, BLOOM, and Mistral. Our findings indicate that LLMs' proficiency in processing a particular language is predominantly due to a small subset of neurons, primarily situated in the models' top and bottom layers. Furthermore, we showcase the feasibility to "steer" the output language of LLMs by selectively activating or deactivating language-specific neurons. Our research provides important evidence to the understanding and exploration of the multilingual capabilities of LLMs.