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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 5578
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment operator followed by True (negative activations)

    python-code · gemini-2.5-flash-lite

    variable 'a' as first argument

    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
    .strip
    -0.02
    (len
    -0.02
     ""
    -0.02
     '
    -0.02
    len
    -0.02
     "
    -0.01
     form
    -0.01
     len
    -0.01
     '#
    -0.01
     '.
    -0.01
    POSITIVE LOGITS
     neighbors
    0.03
     Example
    0.02
     directions
    0.02
    _neighbors
    0.02
    hild
    0.02
     adjac
    0.02
    _neighbor
    0.02
     adj
    0.02
    fset
    0.02
     new
    0.02
    Activations Density 99.181%

    No Known Activations