© 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. 3767
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string representation formatting

    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
    39
    -0.04
    47
    -0.04
    45
    -0.04
    37
    -0.04
    38
    -0.04
    49
    -0.04
    42
    -0.04
    48
    -0.04
    36
    -0.03
    43
    -0.03
    POSITIVE LOGITS
    u
    0.02
    stance
    0.02
    ual
    0.02
    ure
    0.02
    iz
    0.02
     app
    0.01
    ©
    0.01
     that
    0.01
    ut
    0.01
    utation
    0.01
    Activations Density 82.341%

    No Known Activations