© 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. 1472
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    argument to parse or writer

    python-code · gemini-2.5-flash-lite

    json.loads (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
    atch
    -0.03
    ver
    -0.03
    fset
    -0.02
     possible
    -0.02
    hor
    -0.02
     directions
    -0.02
     neighbors
    -0.01
     adjac
    -0.01
     moves
    -0.01
     to
    -0.01
    POSITIVE LOGITS
     float
    0.04
    ash
    0.04
     ob
    0.04
     queue
    0.04
     str
    0.04
    oc
    0.03
     iter
    0.03
     network
    0.03
    q
    0.03
    array
    0.03
    Activations Density 95.722%

    No Known Activations