© 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. 2397
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    statistics.stdev

    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
    oth
    -0.03
    in
    -0.02
    .in
    -0.02
    out
    -0.02
    Error
    -0.02
     Returns
    -0.02
     Example
    -0.02
    No
    -0.01
     Return
    -0.01
     List
    -0.01
    POSITIVE LOGITS
    [v
    0.07
    (v
    0.07
     v
    0.06
    .b
    0.06
    _b
    0.05
    v
    0.05
     bre
    0.05
    Ĥ
    0.05
    B
    0.05
     B
    0.05
    Activations Density 15.665%

    No Known Activations