© 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. 983
    Prev
    Next
    INDEX
    Explanations

    division or modulo operator (negative activations)

    python-code · gemini-2.5-flash-lite

    self.grades or range(

    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
     instruction
    -0.38
     instructions
    -0.33
    struction
    -0.29
    structions
    -0.27
    gram
    -0.24
    mory
    -0.24
    gist
    -0.21
    mmand
    -0.18
    oin
    -0.17
     command
    -0.17
    POSITIVE LOGITS
     optimal
    0.18
    .remove
    0.08
    ud
    0.08
    _per
    0.07
    ig
    0.07
    oc
    0.05
    ist
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    Activations Density 100.000%

    No Known Activations