© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2514
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    collections.Counter usage

    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
    ens
    -0.03
    en
    -0.02
     en
    -0.02
    En
    -0.02
    ener
    -0.01
    (de
    -0.01
    .he
    -0.01
     &
    -0.01
    ment
    -0.01
    _of
    -0.01
    POSITIVE LOGITS
    .read
    0.06
    .write
    0.05
    ize
    0.04
    ilities
    0.04
    iz
    0.03
    strip
    0.03
    ized
    0.03
    .txt
    0.03
    lines
    0.03
    (filename
    0.03
    Activations Density 37.797%

    No Known Activations