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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 1951
    Prev
    Next
    INDEX
    Explanations

    numeric literals in lists or coordinates (negative activations)

    python-code · gemini-2.5-flash-lite

    sqlite3.connect

    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
    ffe
    -0.13
    ac
    -0.09
    .in
    -0.08
    ad
    -0.08
    ce
    -0.07
    de
    -0.06
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    set
    0.38
    ly
    0.37
    import
    0.36
    instance
    0.33
    Node
    0.32
    list
    0.31
    path
    0.30
    line
    0.29
    ari
    0.26
    or
    0.26
    Activations Density 89.781%

    No Known Activations