© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    shuffle method call argument (negative activations)

    python-code · gemini-2.5-flash-lite

    end of statement or argument

    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
    un
    -0.06
    ve
    -0.06
    start
    -0.06
    if
    -0.05
    co
    -0.04
     comp
    -0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
    ss
    0.30
    um
    0.18
    ct
    0.17
    ap
    0.15
    ls
    0.14
    te
    0.13
    os
    0.11
    pe
    0.11
    es
    0.10
     each
    0.10
    Activations Density 100.000%

    No Known Activations