© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 7802
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    lambda expression or for loop (negative activations)

    python-code · gemini-2.5-flash-lite

    `.co` followed by `unt`

    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
    |>
    -0.04
    lit
    -0.03
    _queue
    -0.02
    rontier
    -0.02
     heap
    -0.02
     :
    -0.02
    ut
    -0.02
    queue
    -0.02
     collections
    -0.02
    isit
    -0.02
    POSITIVE LOGITS
     it
    0.04
     or
    0.02
    V
    0.01
     V
    0.01
    .m
    0.01
     each
    0.01
    _type
    0.01
     problem
    0.01
    ?
    0.01
    į
    0.00
    Activations Density 95.186%

    No Known Activations