© 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. 4603
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    comparison operators or in keyword (negative activations)

    python-code · gemini-2.5-flash-lite

    dunder methods and attributes

    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
     I
    -0.17
    I
    -0.09
    =True
    -0.05
    The
    -0.03
    iven
    -0.03
     The
    -0.03
    ag
    -0.02
     This
    -0.02
     as
    -0.02
     each
    -0.02
    POSITIVE LOGITS
    ((
    0.06
    array
    0.05
     np
    0.04
    id
    0.04
    resh
    0.04
    reshold
    0.03
    dices
    0.03
    ray
    0.03
     float
    0.03
     ob
    0.02
    Activations Density 23.385%

    No Known Activations