© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 1766
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `assert` keyword usages

    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
    Negative Logits
    ulate
    -0.02
    tive
    -0.02
     optim
    -0.02
    el
    -0.01
    th
    -0.01
    per
    -0.01
    ti
    -0.01
     cost
    -0.01
     data
    -0.01
    al
    -0.01
    POSITIVE LOGITS
     has
    0.04
     is
    0.04
    s
    0.04
     can
    0.04
     are
    0.03
    .is
    0.03
     we
    0.02
    n
    0.02
    dict
    0.01
    ss
    0.01
    Activations Density 25.026%

    No Known Activations