© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5574
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    np.linalg function calls

    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
    rt
    -0.03
     all
    -0.03
    all
    -0.03
     any
    -0.02
    ly
    -0.01
     rows
    -0.01
     each
    -0.01
    ree
    -0.01
    (
    -0.01
    _graph
    -0.01
    POSITIVE LOGITS
    inal
    0.06
    rite
    0.05
    ep
    0.04
    ine
    0.03
    ain
    0.03
    ke
    0.03
    in
    0.03
    gram
    0.03
    form
    0.03
    ination
    0.03
    Activations Density 83.169%

    No Known Activations