© 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. 2-MLP
    11. 3335
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    .y assignment or operation

    python-code · gemini-2.5-flash-lite

    else block start (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
    _coordinates
    -0.11
     obstac
    -0.10
     coordinates
    -0.10
    _coords
    -0.09
    ordinate
    -0.09
     coord
    -0.08
    ordinates
    -0.08
     directions
    -0.06
     dx
    -0.06
    _positions
    -0.06
    POSITIVE LOGITS
    rap
    0.03
    uild
    0.03
     build
    0.03
    uil
    0.02
     instruction
    0.02
     instructions
    0.02
     tree
    0.02
    struction
    0.02
    text
    0.02
    tier
    0.02
    Activations Density 100.000%

    No Known Activations