© 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. 6270
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    keyword `in` range parameters (negative activations)

    python-code · gemini-2.5-flash-lite

    for loop iteration or attribute access

    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
     dp
    -0.03
     while
    -0.03
     iter
    -0.03
     dfs
    -0.03
     heapq
    -0.03
    .pop
    -0.03
     queue
    -0.02
    _comb
    -0.02
    .index
    -0.02
     solve
    -0.02
    POSITIVE LOGITS
    .e
    0.05
     continue
    0.05
    [neighbor
    0.04
    None
    0.04
     None
    0.04
     >
    0.04
    for
    0.04
    hildren
    0.04
    ighbour
    0.03
    neighbor
    0.03
    Activations Density 99.983%

    No Known Activations