© 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. 4054
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `.isnull` and `.isnan` methods

    python-code · gemini-2.5-flash-lite

    assignment to self (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
    A
    -0.04
     on
    -0.04
    on
    -0.03
     A
    -0.03
     contin
    -0.03
    _al
    -0.02
    one
    -0.02
    (e
    -0.01
    _an
    -0.01
    -0.01
    POSITIVE LOGITS
    actions
    0.06
    apping
    0.06
    loor
    0.06
    ariable
    0.06
    dint
    0.05
    erge
    0.05
    lif
    0.05
    assign
    0.05
    gree
    0.05
    ariables
    0.05
    Activations Density 100.000%

    No Known Activations