© 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. 4024
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    condition `if` statement (negative activations)

    python-code · gemini-2.5-flash-lite

    function calls after variable assignment

    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
    und
    -0.02
     initial
    -0.01
     Output
    -0.01
    _edges
    -0.01
     next
    -0.01
    pected
    -0.01
     return
    -0.01
    uild
    -0.01
     not
    -0.01
     con
    -0.01
    POSITIVE LOGITS
     Example
    0.03
     Testing
    0.02
    ak
    0.02
    _grid
    0.02
     Test
    0.02
    ample
    0.02
    iven
    0.02
    structions
    0.01
    [(
    0.01
     grid
    0.01
    Activations Density 66.317%

    No Known Activations