© 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. 5000
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    assignment or return statements involving str (negative activations)

    python-code · gemini-2.5-flash-lite

    type hints for int and list

    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
    's
    -0.04
    ]][
    -0.02
     ((
    -0.02
     and
    -0.02
    ][
    -0.02
     \
    -0.02
    _str
    -0.02
     [[
    -0.01
    _string
    -0.01
    =
    -0.01
    POSITIVE LOGITS
     None
    0.05
    lable
    0.05
    None
    0.05
    (int
    0.04
    (con
    0.03
     {↵
    0.03
    (d
    0.03
    reshold
    0.03
    ion
    0.03
    join
    0.03
    Activations Density 99.128%

    No Known Activations