© 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. 5511
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    optimizer or date

    python-code · gemini-2.5-flash-lite

    comma in lists or arguments (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
     break
    -0.06
    _to
    -0.04
    ulation
    -0.04
     while
    -0.03
    ility
    -0.03
    _from
    -0.03
    imum
    -0.03
    ilities
    -0.03
    ination
    -0.03
    ness
    -0.03
    POSITIVE LOGITS
    /
    0.03
    unc
    0.03
    _un
    0.03
    unction
    0.03
    ters
    0.03
    ter
    0.03
     usage
    0.03
    rue
    0.03
    ut
    0.03
     U
    0.02
    Activations Density 100.000%

    No Known Activations