© 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. MLP
    9. 6-MLP
    11. 4035
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call argument (negative activations)

    python-code · gemini-2.5-flash-lite

    indexing with integers or variables

    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
     comb
    -0.04
    ê
    -0.02
    ì
    -0.02
    í
    -0.02
    ë
    -0.02
     open
    -0.01
    .s
    -0.01
    °
    -0.01
     a
    -0.00
    '
    0.00
    POSITIVE LOGITS
    rior
    0.02
    lose
    0.02
     set
    0.01
    º
    0.01
    uration
    0.01
    ies
    0.01
    ï
    0.01
    İ
    0.01
    ĭ
    0.01
    alue
    0.01
    Activations Density 99.809%

    No Known Activations