© 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. 1468
    Prev
    Next
    INDEX
    Explanations

    keywords related to directories (negative activations)

    python-code · gemini-2.5-flash-lite

    return statement tuple

    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
    values
    -0.07
    ;
    -0.03
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    POSITIVE LOGITS
    put
    0.27
     U
    0.14
    ase
    0.12
    ile
    0.12
     valid
    0.10
    .append
    0.09
    ol
    0.07
    us
    0.07
     In
    0.06
    y
    0.04
    Activations Density 99.979%

    No Known Activations