© 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. 1382
    Prev
    Next
    INDEX
    Explanations

    for `e` in and`else` branches (negative activations)

    python-code · gemini-2.5-flash-lite

    email variable in string processing

    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
    arehouse
    -0.19
    ater
    -0.11
    mit
    -0.08
    8
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
    red
    0.29
    re
    0.23
     represent
    0.17
     read
    0.16
    ost
    0.16
    res
    0.15
    gre
    0.15
    R
    0.14
    _re
    0.13
    rection
    0.12
    Activations Density 99.988%

    No Known Activations