© 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. 2-MLP
    11. 6161
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    np.dot function call

    python-code · gemini-2.5-flash-lite

    appending to children list (negative activations)

    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
     heuristic
    -0.09
    uristic
    -0.08
    rect
    -0.07
    oal
    -0.06
    rontier
    -0.06
     goal
    -0.06
    rior
    -0.06
    ateg
    -0.05
    istic
    -0.05
    ct
    -0.05
    POSITIVE LOGITS
     new
    0.06
    jkstra
    0.05
    new
    0.05
    (new
    0.05
    ~
    0.05
    lambda
    0.04
    old
    0.04
    (str
    0.04
    (int
    0.04
    %
    0.03
    Activations Density 100.000%

    No Known Activations