© 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
    2. OpenAI · Weight-Sparse Transformers
    3. CircuitGPT-Python
    4. Residual Stream
    5. 7-RESID
    6. 1689
    Prev
    Next
    INDEX
    Explanations

    method call separator with attribute (negative activations)

    python-code · gemini-2.5-flash-lite

    accessing dictionary key

    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
    values
    -0.05
    (),
    -0.03
    loc
    -0.03
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    POSITIVE LOGITS
    .↵↵
    0.28
    .↵
    0.28
    ."""↵
    0.20
    """↵
    0.06
    append
    0.05
     algorithm
    0.05
    print
    0.04
    direction
    0.03
     else
    0.03
    '
    0.00
    Activations Density 100.000%

    No Known Activations