© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    modulo operator or integer division (negative activations)

    python-code · gemini-2.5-flash-lite

    call followed by a comma

    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
    [current
    -0.04
     random
    -0.02
    &
    0.00
    #
    0.00
    '
    0.00
    *
    0.00
    %
    0.00
    )
    0.00
    !
    0.00
    "
    0.00
    POSITIVE LOGITS
    [start
    0.24
    (start
    0.22
     start
    0.18
    start
    0.17
    .start
    0.13
    end
    0.10
    endoftext
    0.09
    art
    0.08
     end
    0.08
    St
    0.05
    Activations Density 100.000%

    No Known Activations