© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 6-MLP
    11. 2178
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    for variable in range (negative activations)

    python-code · gemini-2.5-flash-lite

    math.radians

    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
    rontier
    -0.09
     visited
    -0.09
    visited
    -0.08
     dfs
    -0.07
    queue
    -0.07
    _queue
    -0.06
    isited
    -0.05
     queue
    -0.05
     stack
    -0.05
     heap
    -0.05
    POSITIVE LOGITS
     base
    0.02
     ra
    0.02
    ari
    0.01
     problem
    0.01
     zip
    0.01
    ?
    0.01
    point
    0.01
    _e
    0.01
    _par
    0.01
    _lo
    0.01
    Activations Density 99.888%

    No Known Activations