© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    assignment or comparison (negative activations)

    python-code · gemini-2.5-flash-lite

    assignment to 'g' in method body

    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
    .index
    -0.24
    .keys
    -0.22
    (range
    -0.16
     start
    -0.09
     list
    -0.05
    0
    -0.02
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    POSITIVE LOGITS
     []↵↵
    0.15
    lauses
    0.14
     [↵
    0.13
     []↵
    0.11
     [(
    0.08
     {↵
    0.05
    '
    0.00
    #
    0.00
    &
    0.00
    %
    0.00
    Activations Density 100.000%

    No Known Activations