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

    Neuronpedia

    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. 4158
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assert statements

    python-code · gemini-2.5-flash-lite

    string.ascii and string.digits (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
    /
    -0.06
    H
    -0.04
    L
    -0.04
    A
    -0.04
    N
    -0.04
    U
    -0.04
    R
    -0.04
    C
    -0.04
    Z
    -0.04
    K
    -0.04
    POSITIVE LOGITS
     representing
    0.09
     that
    0.06
     given
    0.06
     the
    0.06
     each
    0.05
    ]][
    0.05
     represe
    0.05
     based
    0.04
     The
    0.04
     and
    0.04
    Activations Density 100.000%

    No Known Activations