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

    Neuronpedia

    INDEX
    Explanations

    numbers and transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RADIATION
    0.43
     있을
    0.42
     있는
    0.41
    有时候
    0.40
    某些
    0.40
     HTTPException
    0.40
    도는
    0.39
    逺
    0.39
    ी
    0.38
    相应的
    0.38
    POSITIVE LOGITS
     antes
    0.47
     प्रत्येक
    0.45
     each
    0.44
     dashboards
    0.43
     jednotliv
    0.42
     upfront
    0.41
    three
    0.41
     ennen
    0.41
     entrees
    0.40
    8
    0.40
    Act Density 0.015%

    No Known Activations