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

    Neuronpedia

    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. 4899
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literal formatting (negative activations)

    python-code · gemini-2.5-flash-lite

    `assertEqual` or `equalsIgnoreCase` assertion

    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
     graph
    -0.01
     grid
    -0.01
     sys
    -0.01
    or
    -0.01
    .split
    -0.01
     population
    -0.01
    lse
    -0.00
     not
    -0.00
    (node
    -0.00
     matrix
    -0.00
    POSITIVE LOGITS
     while
    0.02
    ][
    0.01
    .append
    0.01
    [(
    0.01
    ((
    0.01
     whi
    0.01
    ode
    0.01
    _edge
    0.01
    use
    0.01
    l
    0.00
    Activations Density 20.078%

    No Known Activations