© 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. 763
    Prev
    Next
    INDEX
    Explanations

    `__init__` or method definition body (negative activations)

    python-code · gemini-2.5-flash-lite

    with statement context

    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
    ç
    -0.17
    æ
    -0.15
    è
    -0.15
    é
    -0.14
    ä
    -0.14
    å
    -0.13
    ī
    -0.05
     op
    -0.05
    °
    -0.02
    '
    0.00
    POSITIVE LOGITS
     open
    0.27
    â
    0.26
    Â
    0.16
    stac
    0.14
    (op
    0.11
    Ķ
    0.05
    _to
    0.05
    _from
    0.04
    queue
    0.04
     to
    0.02
    Activations Density 100.000%

    No Known Activations