© 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. 6203
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis or bracket (negative activations)

    python-code · gemini-2.5-flash-lite

    calling constructor or method

    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
     while
    -0.04
    tion
    -0.02
    No
    -0.02
    from
    -0.02
    ner
    -0.02
     n
    -0.02
    istic
    -0.02
    .n
    -0.02
     nx
    -0.01
    sible
    -0.01
    POSITIVE LOGITS
     graph
    0.02
    hor
    0.01
     grid
    0.01
    or
    0.01
     population
    0.01
    ķ
    0.01
     matrix
    0.01
     representing
    0.01
     directions
    0.01
     obstac
    0.01
    Activations Density 60.582%

    No Known Activations