© 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. 1995
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call ends with .is

    python-code · gemini-2.5-flash-lite

    initialization parameters in class definition (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
    1
    -0.05
     [
    -0.04
    unt
    -0.04
    _from
    -0.03
    _to
    -0.03
     from
    -0.03
    count
    -0.03
    ount
    -0.03
     to
    -0.03
     whi
    -0.03
    POSITIVE LOGITS
    ig
    0.03
    ci
    0.03
    inary
    0.02
    city
    0.02
    term
    0.01
    .pop
    0.01
    he
    0.01
     the
    0.01
     code
    0.01
    No
    0.01
    Activations Density 99.991%

    No Known Activations