# WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior

arXiv: https://arxiv.org/abs/2603.18474 · HTML: https://mlsanity.com/paper/2603.18474/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 9 of 9)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Language-agnostic BERT Sentence Embedding](https://mlsanity.com/paper/2007.01852/) (2020)
- [Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks](https://mlsanity.com/paper/2511.19265/) (2025)
- [Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering](https://mlsanity.com/paper/2602.04903/) (2026)

## Built on by (most cited first, 1 of 1)

- [MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation](https://mlsanity.com/paper/2609.38718/) (2026)

## Abstract (arXiv)

Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training costs, lack natural language controllability, or compromise semantic coherence. To bridge this gap, we propose WASD (unWeaving Actionable Sufficient Directives), a novel framework that explains model behavior by identifying sufficient neural conditions for token generation. Our method represents candidate conditions as neuron-activation predicates and iteratively searches for a minimal set that guarantees the current output under input perturbations. Experiments on SST-2 and CounterFact with the Gemma-2-2B model demonstrate that our approach produces explanations that are more stable, accurate, and concise than conventional attribution graphs. Moreover, through a case study on controlling cross-lingual output generation, we validated the practical effectiveness of WASD in controlling model behavior.