© 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. 4168
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    function call or definition (negative activations)

    python-code · gemini-2.5-flash-lite

    .geometry('str')

    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
    ized
    -0.05
    ated
    -0.04
    rences
    -0.04
     end
    -0.04
    ic
    -0.04
    ode
    -0.04
    ation
    -0.04
    ted
    -0.03
    red
    -0.03
    ment
    -0.03
    POSITIVE LOGITS
    ry
    0.05
    ri
    0.05
    able
    0.02
    or
    0.02
    am
    0.02
     second
    0.02
    _i
    0.02
     import
    0.01
     graph
    0.01
     grid
    0.00
    Activations Density 96.527%

    No Known Activations