© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    class definition followed by __init__ (negative activations)

    python-code · gemini-2.5-flash-lite

    method call after dot

    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
     directions
    -0.12
    class
    -0.12
     max
    -0.07
    def
    -0.05
     f
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    <|
    0.26
    lse
    0.24
     main
    0.18
     solve
    0.12
     run
    0.12
    main
    0.11
     True
    0.11
    if
    0.09
     Output
    0.07
    <extra_output_id:2047>
    0.07
    Activations Density 100.000%

    No Known Activations