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

    Neuronpedia

    INDEX
    Explanations

    Mat

    np_max-act · gemini-2.0-flash

    The neuron activates on Java OpenCV API class and method tokens (e.g. Mat, Of, Point, Imgproc) indicating it’s looking for OpenCV-related code elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    地
    -0.07
    overlap
    -0.07
    _surface
    -0.07
    เต
    -0.06
    Negative
    -0.06
     nějak
    -0.06
     čím
    -0.06
    Selective
    -0.06
    血
    -0.06
     hoàn
    -0.06
    POSITIVE LOGITS
     Loy
    0.07
    icester
    0.07
    .surname
    0.07
     CR
    0.06
     réalis
    0.06
    -Identifier
    0.06
     educational
    0.06
     Akron
    0.06
     dirig
    0.06
    .AddModelError
    0.06
    Act Density 0.015%

    No Known Activations