© 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. 1148
    Prev
    Next
    INDEX
    Explanations

    HTTP handler class names (negative activations)

    python-code · gemini-2.5-flash-lite

    class keyword followed by identifier

    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
    .in
    -0.13
    None
    -0.08
    (i
    -0.07
     can
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
    _city
    0.29
    .parent
    0.29
    _distances
    0.26
    _capacity
    0.25
    _room
    0.24
    |>
    0.23
    _locations
    0.22
    _times
    0.22
    _loc
    0.21
    _neighbor
    0.20
    Activations Density 100.000%

    No Known Activations