© 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. 3770
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `np.array` or function 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
    yp
    -0.06
     np
    -0.05
    [n
    -0.04
    ique
    -0.03
     ny
    -0.03
    (n
    -0.03
     n
    -0.03
    .n
    -0.03
    _n
    -0.02
     ""
    -0.02
    POSITIVE LOGITS
    on
    0.03
    erge
    0.03
     update
    0.02
    -
    0.02
    ble
    0.02
    update
    0.02
    ink
    0.01
    one
    0.01
    ap
    0.01
     -
    0.01
    Activations Density 60.111%

    No Known Activations