© 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. 6-MLP
    11. 4743
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    zero after colon

    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
    -0.04
    .split
    -0.04
    (v
    -0.04
     if
    -0.02
     +=
    -0.02
     int
    -0.02
     while
    -0.02
     If
    -0.02
    split
    -0.02
    .read
    -0.02
    POSITIVE LOGITS
    timal
    0.02
    losest
    0.02
    |>
    0.02
     optimal
    0.02
    ateg
    0.02
     best
    0.02
     closest
    0.01
    gest
    0.01
    arest
    0.01
     shortest
    0.01
    Activations Density 86.548%

    No Known Activations