© 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. 1593
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    self in method definitions

    python-code · gemini-2.5-flash-lite

    `return` followed by `[` or `(` (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
     dp
    -0.04
    _comb
    -0.02
    _counts
    -0.02
     possible
    -0.02
     comb
    -0.02
    _sum
    -0.02
    inations
    -0.02
     best
    -0.01
     paths
    -0.01
    ination
    -0.01
    POSITIVE LOGITS
    input
    0.06
    .txt
    0.04
     input
    0.04
    _input
    0.04
    (input
    0.04
    ample
    0.03
    .read
    0.03
    structions
    0.03
    En
    0.03
     lines
    0.02
    Activations Density 99.568%

    No Known Activations