© 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. 5994
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    method call parenthesis (negative activations)

    python-code · gemini-2.5-flash-lite

    `range` function calls

    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
    ion
    -0.08
    uple
    -0.05
     zip
    -0.04
     between
    -0.03
    ip
    -0.03
    1
    -0.02
    (start
    -0.02
     first
    -0.02
    get
    -0.01
    _f
    -0.00
    POSITIVE LOGITS
    und
    0.03
    up
    0.03
    ener
    0.02
     range
    0.02
     None
    0.02
     False
    0.02
     the
    0.02
     True
    0.02
    on
    0.01
    (st
    0.01
    Activations Density 99.593%

    No Known Activations