© 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. 602
    Prev
    Next
    INDEX
    Explanations

    module names (negative activations)

    python-code · gemini-2.5-flash-lite

    sha256 function calls

    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
    _x
    -0.05
    _di
    -0.05
     o
    -0.04
    _y
    -0.04
     si
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    POSITIVE LOGITS
    (op
    0.31
    _op
    0.27
    op
    0.27
     op
    0.24
    ush
    0.22
     optimal
    0.18
     oper
    0.13
     optim
    0.13
     O
    0.10
     operation
    0.09
    Activations Density 100.000%

    No Known Activations