# Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?

arXiv: https://arxiv.org/abs/2604.11802 · HTML: https://mlsanity.com/paper/2604.11802/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 18 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [Evaluating and Inducing Personality in Pre-trained Language Models](https://mlsanity.com/paper/2206.07550/) (2022)
- [Personality Alignment of Large Language Models](https://mlsanity.com/paper/2408.11779/) (2024)
- [Large Language Models Can Infer Psychological Dispositions of Social Media Users](https://mlsanity.com/paper/2309.08631/) (2023)
- [Finding Experts in Transformer Models](https://mlsanity.com/paper/2005.07647/) (2020)
- [LLMs Simulate Big Five Personality Traits: Further Evidence](https://mlsanity.com/paper/2402.01765/) (2024)
- [Are LLMs effective psychological assessors? Leveraging adaptive RAG for interpretable mental health screening through psychometric practice](https://mlsanity.com/paper/2501.00982/) (2025)
- [Probing then Editing Response Personality of Large Language Models](https://mlsanity.com/paper/2504.10227/) (2025)
- [Localizing Persona Representations in LLMs](https://mlsanity.com/paper/2505.24539/) (2025)

## Abstract (arXiv)

Using psychological constructs such as the Big Five, large language models (LLMs) can imitate specific personality profiles and predict a user's personality. While LLMs can exhibit behaviors consistent with these constructs, it remains unclear where and how they are represented inside the model and how they relate to behavioral outputs. To address this gap, we focus on questionnaire-operationalized Big Five concepts, analyze the formation and localization of their internal representations, and use interventions to examine how these representations relate to behavioral outputs. In our experiment, we first use probing to examine where Big Five information emerges across model depth. We then identify neurons that respond selectively to each Big Five concept and test whether enhancing or suppressing their activations can bias latent representations and label generation in intended directions. We find that Big Five information becomes rapidly decodable in early layers and remains detectable through the final layers, while concept-selective neurons are most prevalent in mid layers and exhibit limited overlap across domains. Interventions on these neurons consistently shift probe readouts toward targeted concepts, with targeted success rates exceeding 0.8 for some concepts, indicating that the model's internal separation of Big Five personality traits can be causally steered. At the label-generation level, the same interventions often bias generated label distributions in the intended directions, but the effects are weaker, more concept-dependent, and often accompanied by cross-trait spillover, indicating that comparable control over generated labels is difficult even with interventions on a large fraction of concept-selective neurons. Overall, our findings reveal a gap between representational control and behavioral control in LLMs.