© 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. 891
    Prev
    Next
    INDEX
    Explanations

    while keyword start (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment to multiple variables

    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
     return
    -0.10
    <|
    -0.08
    hi
    -0.06
    re
    -0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
     parse
    0.35
    par
    0.21
    loat
    0.14
    .strip
    0.13
    .split
    0.12
     E
    0.10
     part
    0.09
    ate
    0.07
     sp
    0.07
     map
    0.07
    Activations Density 99.996%

    No Known Activations