© 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. 2163
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    if statement structure (negative activations)

    python-code · gemini-2.5-flash-lite

    argument of sys.argv

    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
    xF
    -0.09
    loat
    -0.05
    self
    -0.04
    all
    -0.03
    .random
    -0.03
    atus
    -0.03
    _neighbor
    -0.03
    ward
    -0.03
     as
    -0.03
    ost
    -0.03
    POSITIVE LOGITS
     the
    0.06
    (N
    0.04
    qrt
    0.03
     def
    0.02
    (map
    0.02
    _path
    0.02
    [int
    0.02
    (len
    0.02
    [t
    0.02
     values
    0.02
    Activations Density 79.212%

    No Known Activations