© 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. 2-MLP
    11. 5526
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    float() constructor

    python-code · gemini-2.5-flash-lite

    self. method call (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
    #
    -0.07
    rect
    -0.07
     #
    -0.06
    print
    -0.05
    ct
    -0.05
    <extra_output_id:2047>
    -0.04
     return
    -0.04
    rior
    -0.04
    graph
    -0.04
     ↵
    -0.04
    POSITIVE LOGITS
    igh
    0.05
     >
    0.05
     has
    0.05
                    ↵
    0.05
    h
    0.05
     <
    0.05
     >=
    0.04
    hest
    0.04
     <=
    0.04
     float
    0.04
    Activations Density 100.000%

    No Known Activations