Neel Nanda
Scholar

Neel Nanda

Google Scholar ID: GLnX3MkAAAAJ
Mechanistic Interpretability Team Lead, Google DeepMind
AIMLAI AlignmentInterpretabilityMechanistic Interpretability
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
8,941
 
H-index
32
 
i10-index
45
 
Publications
20
 
Co-authors
9
list available
Contact
Emailneelnanda27@gmail.comTwitterOpen ↗
Publications
35 items
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
2026
Cited
0
Simple LLM Baselines are Competitive for Model Diffing
2026
Cited
0
Emergent Misalignment is Easy, Narrow Misalignment is Hard
2026
Cited
0
What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
2026
Cited
0
Building Production-Ready Probes For Gemini
2026
Cited
1
Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit
2025
Cited
0
Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
2025
Cited
0
Difficulties with Evaluating a Deception Detector for AIs
2025
Cited
0
Resume (English only)
Co-authors
9 total
Arthur Conmy
Arthur Conmy
Google DeepMind
Senthooran Rajamanoharan
Senthooran Rajamanoharan
Google DeepMind
Co-author 3
Co-author 3
Wes Gurnee
Wes Gurnee
Anthropic
Co-author 5
Co-author 5
Catherine Olsson
Catherine Olsson
Anthropic
Lawrence Chan
Lawrence Chan
PhD Student, UC Berkeley
Bilal Chughtai
Bilal Chughtai
Google DeepMind