© 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. 4949
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    string literals and function calls (negative activations)

    python-code · gemini-2.5-flash-lite

    command assignment and keyword arguments

    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
    Ö
    -0.04
     Testing
    -0.03
     Check
    -0.03
     Def
    -0.03
     Get
    -0.03
     Calculate
    -0.03
     Initialize
    -0.03
     Define
    -0.03
    Æ
    -0.03
    split
    -0.03
    POSITIVE LOGITS
    (re
    0.02
     as
    0.01
    n
    0.01
     raise
    0.01
    (key
    0.01
    par
    0.01
     open
    0.01
    get
    0.00
    0.00
    valid
    0.00
    Activations Density 97.787%

    No Known Activations