© 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. 827
    Prev
    Next
    INDEX
    Explanations

    parentheses after function definition (negative activations)

    python-code · gemini-2.5-flash-lite

    string lower or upper method calls

    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
    Ń
    -0.26
    mb
    -0.09
    main
    -0.07
    ¡
    -0.07
    route
    -0.05
    ().
    -0.05
    graph
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    low
    0.27
    liver
    0.25
     up
    0.24
    up
    0.23
     low
    0.20
    light
    0.17
    stra
    0.16
    gest
    0.11
    rans
    0.10
    ater
    0.09
    Activations Density 100.000%

    No Known Activations