# On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons

arXiv: https://arxiv.org/abs/2404.02431 · HTML: https://mlsanity.com/paper/2404.02431/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 33 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Builds on (most cited first, 10 of 10)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Do Llamas Work in English? On the Latent Language of Multilingual Transformers](https://mlsanity.com/paper/2402.10588/) (2024)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM's Translation Capability](https://mlsanity.com/paper/2305.10266/) (2023)
- [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)
- [Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models](https://mlsanity.com/paper/2205.02023/) (2022)
- [Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models](https://mlsanity.com/paper/2210.14328/) (2022)

## Built on by (most cited first, 30 of 83)

- [Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2412.02104/) (2024)
- [Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models](https://mlsanity.com/paper/2504.04264/) (2025)
- [Visual Large Language Models for Generalized and Specialized Applications](https://mlsanity.com/paper/2501.02765/) (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)
- [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)
- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (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)
- [Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation](https://mlsanity.com/paper/2404.11201/) (2024)
- [Multilingual Knowledge Editing with Language-Agnostic Factual Neurons](https://mlsanity.com/paper/2406.16416/) (2024)
- [Multilingual Large Language Models: A Systematic Survey](https://mlsanity.com/paper/2411.11072/) (2024)
- [Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation](https://mlsanity.com/paper/2507.22608/) (2025)
- [Disentangling Language and Culture for Evaluating Multilingual Large Language Models](https://mlsanity.com/paper/2505.24635/) (2025)
- [Knowledge Localization: Mission Not Accomplished? Enter Query Localization!](https://mlsanity.com/paper/2405.14117/) (2024)
- [Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2505.05111/) (2025)
- [RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs](https://mlsanity.com/paper/2502.07424/) (2025)
- [CLaS-Bench: A Cross-Lingual Alignment and Steering Benchmark](https://mlsanity.com/paper/2601.08331/) (2026)
- [Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models](https://mlsanity.com/paper/2502.15639/) (2025)
- [Language-specific Neurons Do Not Facilitate Cross-Lingual Transfer](https://mlsanity.com/paper/2503.17456/) (2025)
- [FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data](https://mlsanity.com/paper/2408.06273/) (2024)
- [Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes](https://mlsanity.com/paper/2410.16930/) (2024)
- [The Translation Barrier Hypothesis: Multilingual Generation with Large Language Models Suffers from Implicit Translation Failure](https://mlsanity.com/paper/2506.22724/) (2025)
- [Beyond the Final Layer: Intermediate Representations for Better Multilingual Calibration in Large Language Models](https://mlsanity.com/paper/2510.03136/) (2025)
- [Understanding Multilingualism in Mixture-of-Experts LLMs: Routing Mechanism, Expert Specialization, and Layerwise Steering](https://mlsanity.com/paper/2601.14050/) (2026)
- [From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons Alignment](https://mlsanity.com/paper/2507.14900/) (2025)
- [Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models](https://mlsanity.com/paper/2505.16538/) (2025)
- [How Does Alignment Enhance LLMs' Multilingual Capabilities? A Language Neurons Perspective](https://mlsanity.com/paper/2505.21505/) (2025)
- [MINER: Mining the Underlying Pattern of Modality-Specific Neurons in Multimodal Large Language Models](https://mlsanity.com/paper/2410.04819/) (2024)

## Abstract (arXiv)

Current decoder-based pre-trained language models (PLMs) successfully demonstrate multilingual capabilities. However, it is unclear how these models handle multilingualism. We analyze the neuron-level internal behavior of multilingual decoder-based PLMs, Specifically examining the existence of neurons that fire ``uniquely for each language'' within decoder-only multilingual PLMs. We analyze six languages: English, German, French, Spanish, Chinese, and Japanese, and show that language-specific neurons are unique, with a slight overlap (< 5%) between languages. These neurons are mainly distributed in the models' first and last few layers. This trend remains consistent across languages and models. Additionally, we tamper with less than 1% of the total neurons in each model during inference and demonstrate that tampering with a few language-specific neurons drastically changes the probability of target language occurrence in text generation.