© 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. 1824
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    loop construct

    python-code · gemini-2.5-flash-lite

    list element assignment (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
    Negative Logits
    _data
    -0.04
    _input
    -0.03
    .b
    -0.02
    .in
    -0.02
     initial
    -0.02
     data
    -0.02
    data
    -0.02
     input
    -0.02
    hildren
    -0.01
    4
    -0.01
    POSITIVE LOGITS
     found
    0.12
    over
    0.06
    _move
    0.04
     for
    0.01
     _
    0.01
    item
    0.01
     num
    0.00
    _path
    0.00
     cell
    0.00
    30
    0.00
    Activations Density 100.000%

    No Known Activations