© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1639
    Prev
    Next
    INDEX
    Explanations

    part of exception handling or button creation (negative activations)

    python-code · gemini-2.5-flash-lite

    divmod and mainloop constructs

    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
    rect
    -0.38
    rior
    -0.31
    ct
    -0.25
    ctor
    -0.20
    ec
    -0.11
    ave
    -0.11
    (w
    -0.07
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    op
    0.16
    m
    0.10
     pos
    0.10
    _w
    0.08
    list
    0.06
    ure
    0.05
    re
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 99.995%

    No Known Activations