© 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. 2-MLP
    11. 6379
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    lambda function arguments

    python-code · gemini-2.5-flash-lite

    self, followed by attribute access (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
    Not in Any Lists

    No Comments

    Negative Logits
    jk
    -0.05
    .edges
    -0.05
    edges
    -0.05
     edges
    -0.05
    _conne
    -0.05
     edge
    -0.05
     Graph
    -0.05
     graph
    -0.04
    _graph
    -0.04
    _edges
    -0.04
    POSITIVE LOGITS
    utation
    0.10
    gth
    0.10
    apping
    0.09
    ÷
    0.09
    Á
    0.09
    ø
    0.09
    þ
    0.09
    À
    0.09
    û
    0.09
    õ
    0.09
    Activations Density 100.000%

    No Known Activations