© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 3866
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    list append method (negative activations)

    python-code · gemini-2.5-flash-lite

    number of attribute

    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
    Not in Any Lists

    No Comments

    Negative Logits
    qrt
    -0.04
    alculate
    -0.03
    ((
    -0.03
    ab
    -0.03
    (current
    -0.02
     ver
    -0.02
     calculate
    -0.02
    (start
    -0.02
    (line
    -0.02
    .set
    -0.02
    POSITIVE LOGITS
     each
    0.06
     rows
    0.04
    .values
    0.04
     col
    0.03
    _nodes
    0.03
     range
    0.03
    .items
    0.03
    udoku
    0.03
     nodes
    0.03
    _cities
    0.03
    Activations Density 98.564%

    No Known Activations