© 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. 1761
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    self. attribute access

    python-code · gemini-2.5-flash-lite

    string literal split or conversion (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
     +=
    -0.03
     import
    -0.02
     sum
    -0.01
     ("
    -0.01
     (
    -0.01
    ness
    -0.01
     ('
    -0.01
     ((
    -0.01
    [(
    -0.01
     us
    -0.01
    POSITIVE LOGITS
    None
    0.05
    alse
    0.04
     None
    0.04
     []↵↵
    0.04
     False
    0.04
     []↵
    0.03
     raise
    0.03
     {}↵↵
    0.03
     ValueError
    0.03
    False
    0.03
    Activations Density 99.333%

    No Known Activations