© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1925
    Prev
    Next
    INDEX
    Explanations

    special method names like __init__ (negative activations)

    python-code · gemini-2.5-flash-lite

    verbose 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
    orted
    -0.36
     sorted
    -0.35
    vers
    -0.20
    ort
    -0.20
    verse
    -0.17
    erge
    -0.13
    lat
    -0.10
    ir
    -0.08
     lon
    -0.07
     qu
    -0.07
    POSITIVE LOGITS
    loc
    0.15
    !
    0.11
     run
    0.11
     en
    0.06
    hi
    0.06
    mp
    0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 100.000%

    No Known Activations