© 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. 6-MLP
    11. 5792
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    `m` followed by `=` or `(`

    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
     heapq
    -0.02
     queue
    -0.02
     stack
    -0.02
     set
    -0.01
     values
    -0.01
     he
    -0.01
     q
    -0.01
    _path
    -0.01
    .pop
    -0.01
    .txt
    -0.01
    POSITIVE LOGITS
     Get
    0.04
     cur
    0.04
     current
    0.04
     curr
    0.03
    current
    0.03
     _
    0.03
     j
    0.02
     u
    0.02
     i
    0.02
     pi
    0.02
    Activations Density 67.859%

    No Known Activations