# Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models

arXiv: https://arxiv.org/abs/2605.30717 · HTML: https://mlsanity.com/paper/2605.30717/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 29 May 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [Gender bias and stereotypes in Large Language Models](https://mlsanity.com/paper/2308.14921/) (2023)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons](https://mlsanity.com/paper/2404.02431/) (2024)
- [Disclosure and Mitigation of Gender Bias in LLMs](https://mlsanity.com/paper/2402.11190/) (2024)
- [Sharing Matters: Analysing Neurons Across Languages and Tasks in LLMs](https://mlsanity.com/paper/2406.09265/) (2024)
- [Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation](https://mlsanity.com/paper/2311.00306/) (2023)
- [Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions](https://mlsanity.com/paper/2306.04597/) (2023)
- [Debiasing Algorithm through Model Adaptation](https://mlsanity.com/paper/2310.18913/) (2023)
- [Style-Specific Neurons for Steering LLMs in Text Style Transfer](https://mlsanity.com/paper/2410.00593/) (2024)
- [Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination](https://mlsanity.com/paper/2311.09627/) (2023)
- [Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challenges](https://mlsanity.com/paper/2301.10075/) (2023)
- [A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation](https://mlsanity.com/paper/2310.12127/) (2023)
- [Multilingual Knowledge Editing with Language-Agnostic Factual Neurons](https://mlsanity.com/paper/2406.16416/) (2024)
- [BiasEdit: Debiasing Stereotyped Language Models via Model Editing](https://mlsanity.com/paper/2503.08588/) (2025)
- [Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions](https://mlsanity.com/paper/2407.05271/) (2024)
- [Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models](https://mlsanity.com/paper/2205.02023/) (2022)
- [In-Contextual Gender Bias Suppression for Large Language Models](https://mlsanity.com/paper/2309.07251/) (2023)
- [Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTE](https://mlsanity.com/paper/2501.09409/) (2025)
- [Unsupervised Concept Vector Extraction for Bias Control in LLMs](https://mlsanity.com/paper/2502.19721/) (2025)
- [Are We Paying Attention to Her? Investigating Gender Disambiguation and Attention in Machine Translation](https://mlsanity.com/paper/2505.08546/) (2025)
- [The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models](https://mlsanity.com/paper/2406.10130/) (2024)
- [The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models](https://mlsanity.com/paper/2410.16672/) (2024)
- [How Programming Concepts and Neurons Are Shared in Code Language Models](https://mlsanity.com/paper/2506.01074/) (2025)
- [CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs](https://mlsanity.com/paper/2510.09871/) (2025)
- [SciPrompt: Knowledge-augmented Prompting for Fine-grained Categorization of Scientific Topics](https://mlsanity.com/paper/2410.01946/) (2024)
- [On Relation-Specific Neurons in Large Language Models](https://mlsanity.com/paper/2502.17355/) (2025)
- [On the Mutual Influence of Gender and Occupation in LLM Representations](https://mlsanity.com/paper/2503.06792/) (2025)
- [Local Contrastive Editing of Gender Stereotypes](https://mlsanity.com/paper/2410.17739/) (2024)

## Built on by (most cited first, 2 of 2)

- [StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs](https://mlsanity.com/paper/2606.20527/) (2026)
- [ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models](https://mlsanity.com/paper/2608.29847/) (2026)

## Abstract (arXiv)

Language models (LMs) can produce gendered language and stereotypes even when given neutral prompts. Most prior work on gender bias in LMs primarily examines gender through a binary lens (feminine vs. masculine), with limited attention to gender-neutral forms, such as they/them pronouns or neutrally phrased job titles. How gender-related signals are encoded in the internal representations of LMs remains an open question. In this work, we study gender-specific neurons in LMs across three categories: feminine, masculine, and gender-neutral. We propose a neuron-level intervention method to identify neurons that are strongly tied to each gender category. We then test these neurons through controlled generation, showing that activating or masking gender-related neurons can steer a sentence toward a target gender form while preserving its original meaning. To evaluate the effectiveness of our gender-intervention approach, we curate two datasets with controlled sentences labeled across all three gender categories and validate the data quality through human evaluation. Experiments on two open-source LMs show that gender-specific neurons are not evenly distributed across model layers; instead, they concentrate heavily in the earliest layers with smaller contributions from later layers. Compared to existing methods, our method achieves more precise gender control, with less leakage into non-target gender categories and stable output quality through two evaluation criteria. Overall, our work examines how gender is encoded in LMs and provides a simple yet effective approach toward controlled gender intervention for both neuron intervention evaluation and gender bias mitigation. Code and datasets are available at: https://github.com/zhiwenyou103/Gender-Neuron-Intervention