© 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. 5566
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    json import or int() argument (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
    .edges
    -0.08
    [u
    -0.07
    .nodes
    -0.07
    [node
    -0.06
     and
    -0.06
    .graph
    -0.06
    .heapp
    -0.06
    .remove
    -0.05
    [neighbor
    -0.05
     _
    -0.05
    POSITIVE LOGITS
    join
    0.10
    lable
    0.08
    alc
    0.06
    dint
    0.05
    ong
    0.05
    (),
    0.05
     **
    0.05
    par
    0.04
     queue
    0.04
    a
    0.04
    Activations Density 94.179%

    No Known Activations