© 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. 2034
    Prev
    Next
    INDEX
    Explanations

    function definition keywords (negative activations)

    python-code · gemini-2.5-flash-lite

    float conversion with string

    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
     %
    -0.09
     that
    -0.07
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    POSITIVE LOGITS
    ":
    0.19
    ':
    0.15
    ↵↵
    0.14
    ↵
    0.12
    <|
    0.11
    <extra_output_id:2047>
    0.11
     }↵
    0.10
    ↵↵↵
    0.09
    ↵    ↵
    0.08
    '
    0.00
    Activations Density 99.973%

    No Known Activations