© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 378
    Prev
    Next
    INDEX
    Explanations

    opening bracket or parenthesis followed by a number

    python-code · gemini-2.5-flash-lite

    dictionary key access or definition (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     g
    -0.24
     e
    -0.23
     b
    -0.23
     d
    -0.23
     p
    -0.22
     s
    -0.22
     f
    -0.21
     m
    -0.20
     h
    -0.20
    _d
    -0.19
    POSITIVE LOGITS
    ."""↵
    0.14
    "{
    0.13
    didate
    0.13
    _cell
    0.12
    ulation
    0.11
    tity
    0.10
    essage
    0.10
    ment
    0.09
    tile
    0.09
    neighbor
    0.08
    Activations Density 99.999%

    No Known Activations