© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    secrets module attribute access (negative activations)

    python-code · gemini-2.5-flash-lite

    function/method call arguments

    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
    -0.16
    .g
    -0.16
    n
    -0.15
    -
    -0.12
    th
    -0.10
    i
    -0.10
    ns
    -0.07
    def
    -0.06
    9
    -0.05
     num
    -0.05
    POSITIVE LOGITS
    <
    0.24
     log
    0.15
    19
    0.09
     th
    0.07
     con
    0.07
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    Activations Density 99.977%

    No Known Activations