© 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. 833
    Prev
    Next
    INDEX
    Explanations

    function definition starter (negative activations)

    python-code · gemini-2.5-flash-lite

    number literal 25

    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
    rack
    -0.23
    _ob
    -0.18
    ob
    -0.14
     ob
    -0.13
    ack
    -0.13
    he
    -0.08
    de
    -0.07
    .f
    -0.07
     e
    -0.06
    '
    0.00
    POSITIVE LOGITS
    ous
    0.40
    el
    0.25
    5
    0.18
    other
    0.12
     char
    0.12
    58
    0.08
    6
    0.05
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 96.346%

    No Known Activations