© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. Residual Stream
    9. 7-RESID
    11. 795
    Prev
    Next
    INDEX
    Explanations

    import or from datetime, time, or collections (negative activations)

    python-code · gemini-2.5-flash-lite

    try except blocks or else statements

    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
     si
    -0.10
    .in
    -0.08
    atus
    -0.07
    _idx
    -0.06
    (st
    -0.06
    _len
    -0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    =lambda
    0.50
    .split
    0.25
    .keys
    0.23
    .values
    0.23
     for
    0.17
     if
    0.15
     as
    0.15
     #
    0.15
     based
    0.14
     with
    0.14
    Activations Density 86.530%

    No Known Activations