© 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. MLP
    9. 6-MLP
    11. 5590
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    division assignment operator (negative activations)

    python-code · gemini-2.5-flash-lite

    range with parentheses

    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
     {↵
    -0.05
     are
    -0.03
    _of
    -0.02
     product
    -0.02
     of
    -0.02
    of
    -0.02
    ber
    -0.02
    th
    -0.00
    '
    0.00
    #
    0.00
    POSITIVE LOGITS
     given
    0.09
    zero
    0.08
     spe
    0.07
     <=
    0.04
    wo
    0.04
     not
    0.03
    ound
    0.03
     input
    0.03
     any
    0.03
    one
    0.02
    Activations Density 99.760%

    No Known Activations