Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    Python code related to machine learning, specifically logistic regression and cost functions.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron is triggered by file‐path construction code, particularly occurrences of “os.path.join” (and its components) used to build directory/file paths.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Uuid
    -0.07
    ::::::
    -0.06
    τικός
    -0.06
    cales
    -0.06
     přek
    -0.06
    {EIF
    -0.06
    chemas
    -0.06
     Wen
    -0.06
     conspic
    -0.06
     empez
    -0.06
    POSITIVE LOGITS
    .getAttribute
    0.06
     agar
    0.06
    _WEB
    0.05
    ност
    0.05
     hydrogen
    0.05
     Recipes
    0.05
     він
    0.05
    母
    0.05
     Rehabilitation
    0.05
     cook
    0.05
    Act Density 0.092%

    No Known Activations