© 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. 1614
    Prev
    Next
    INDEX
    Explanations

    call arguments or method parameters (negative activations)

    python-code · gemini-2.5-flash-lite

    dot format

    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
    gor
    -0.10
    49
    -0.09
    ger
    -0.07
    (range
    -0.05
    fig
    -0.04
    (str
    -0.03
    lo
    -0.02
    b
    -0.01
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
     z
    0.24
    Z
    0.22
    z
    0.21
    zz
    0.21
    47
    0.08
    ru
    0.07
     zip
    0.04
     plt
    0.04
    .grid
    0.03
    '
    0.00
    Activations Density 94.519%

    No Known Activations