© 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. 7042
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    send_header or end_headers

    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
    .strip
    -0.11
    .split
    -0.05
    code
    -0.04
    per
    -0.03
    is
    -0.03
     or
    -0.03
    ain
    -0.03
    e
    -0.03
    .f
    -0.03
    t
    -0.02
    POSITIVE LOGITS
    ad
    0.08
     set
    0.05
    ave
    0.05
    uristic
    0.05
    60
    0.05
    st
    0.04
    are
    0.03
    46
    0.03
    A
    0.03
    ck
    0.03
    Activations Density 62.600%

    No Known Activations