© 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. 480
    Prev
    Next
    INDEX
    Explanations

    list indexing or function call argument

    python-code · gemini-2.5-flash-lite

    print function calls (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
    ¼
    -0.25
    area
    -0.18
     algorithm
    -0.16
    assign
    -0.16
     action
    -0.16
     ar
    -0.15
     assign
    -0.15
     ad
    -0.15
    actions
    -0.14
    ass
    -0.14
    POSITIVE LOGITS
    _neighbors
    0.16
     neighbors
    0.14
    ec
    0.13
     file
    0.12
    (file
    0.11
    (neighbor
    0.11
    _neighbor
    0.10
    ile
    0.09
    _file
    0.09
    neighbor
    0.08
    Activations Density 99.841%

    No Known Activations