© 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. 550
    Prev
    Next
    INDEX
    Explanations

    `itemgetter` or `choices` function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    clear() or parse or operator or .case

    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
    dates
    -0.30
    ask
    -0.29
    item
    -0.26
    asks
    -0.25
    ra
    -0.20
     item
    -0.19
    per
    -0.14
    om
    -0.11
    d
    -0.07
    r
    -0.07
    POSITIVE LOGITS
    ar
    0.26
    are
    0.20
    ay
    0.13
    ars
    0.12
    al
    0.11
    (pro
    0.09
    H
    0.07
     s
    0.03
    '
    0.00
    #
    0.00
    Activations Density 94.655%

    No Known Activations