© 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. 3176
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    closing parenthesis or 'raise' statement (negative activations)

    python-code · gemini-2.5-flash-lite

    `pass` statement or class definition

    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
     each
    -0.05
    }:
    -0.05
     continue
    -0.05
    ron
    -0.04
     start
    -0.04
     heap
    -0.04
     first
    -0.04
     source
    -0.04
    start
    -0.04
     heapq
    -0.04
    POSITIVE LOGITS
    mple
    0.07
    instance
    0.07
    ome
    0.06
     representing
    0.05
    ized
    0.05
    ic
    0.04
    rences
    0.04
     other
    0.04
    init
    0.04
    ode
    0.04
    Activations Density 99.999%

    No Known Activations