© 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. 745
    Prev
    Next
    INDEX
    Explanations

    year or fetchall (negative activations)

    python-code · gemini-2.5-flash-lite

    attribute access or assignment

    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
    dict
    -0.13
    ed
    -0.08
    im
    -0.06
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    POSITIVE LOGITS
    ors
    0.26
    zero
    0.24
    or
    0.24
    our
    0.23
    order
    0.21
    rence
    0.16
    one
    0.15
    umn
    0.15
    ore
    0.15
    O
    0.12
    Activations Density 100.000%

    No Known Activations