© 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. 662
    Prev
    Next
    INDEX
    Explanations

    assignment to tuple or function call (negative activations)

    python-code · gemini-2.5-flash-lite

    self access to attributes

    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
    (points
    -0.10
    (point
    -0.06
    ap
    -0.03
    st
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    POSITIVE LOGITS
     pos
    0.29
     positions
    0.25
    _pos
    0.25
     position
    0.23
    _positions
    0.23
    _position
    0.18
    osition
    0.14
    .position
    0.13
     possible
    0.11
     nx
    0.10
    Activations Density 100.000%

    No Known Activations