© 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. 6130
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    random calls or function definition (negative activations)

    python-code · gemini-2.5-flash-lite

    random function calls

    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
    (range
    -0.08
    (grid
    -0.04
    (matrix
    -0.04
    (board
    -0.04
    oard
    -0.04
    (graph
    -0.04
    blem
    -0.04
     or
    -0.04
    grid
    -0.04
    _grid
    -0.03
    POSITIVE LOGITS
    [c
    0.07
     of
    0.07
    |>
    0.06
    of
    0.06
    lit
    0.06
    (c
    0.05
     =
    0.04
     next
    0.04
    _of
    0.04
    _m
    0.04
    Activations Density 28.961%

    No Known Activations