© 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. 3722
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or comparison

    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
     <=
    -0.05
    ound
    -0.04
     any
    -0.04
    .is
    -0.03
    mple
    -0.03
     >=
    -0.03
    init
    -0.03
     If
    -0.03
     while
    -0.02
    The
    -0.02
    POSITIVE LOGITS
     each
    0.05
    }:
    0.03
    .ch
    0.03
    str
    0.03
     St
    0.03
     Get
    0.03
     str
    0.03
    (str
    0.03
     ch
    0.02
     char
    0.02
    Activations Density 85.803%

    No Known Activations