© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    sqlite3.connect (negative activations)

    python-code · gemini-2.5-flash-lite

    method definition after class or import

    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
     function
    -0.13
    ver
    -0.06
    ar
    -0.04
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    *
    0.00
    )
    0.00
    !
    0.00
    POSITIVE LOGITS
    lass
    0.28
    thod
    0.21
     c
    0.16
     __
    0.15
    stance
    0.14
    od
    0.12
     me
    0.11
     st
    0.10
     id
    0.10
     ob
    0.09
    Activations Density 89.412%

    No Known Activations