© 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. 1218
    Prev
    Next
    INDEX
    Explanations

    variable assignment or usage (negative activations)

    python-code · gemini-2.5-flash-lite

    json dumps or multiprocessing

    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
    one
    -0.26
    pe
    -0.24
    use
    -0.14
    per
    -0.11
    ut
    -0.10
    f
    -0.08
     if
    -0.05
    '
    0.00
    #
    0.00
    &
    0.00
    POSITIVE LOGITS
    ithm
    0.46
    ing
    0.32
    mple
    0.18
    ings
    0.17
    at
    0.14
    ine
    0.11
    en
    0.08
    a
    0.04
    '
    0.00
    #
    0.00
    Activations Density 98.648%

    No Known Activations