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

    Neuronpedia

    INDEX
    Explanations

    function definitions and arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المثال
    0.44
    Resposta
    0.42
     sculptural
    0.40
    ânica
    0.40
     Elektrokhimiya
    0.40
    GetHeight
    0.40
     Trichodesmium
    0.40
     ауто
    0.39
     ഇങ്ങനെ
    0.39
     ROUILLER
    0.39
    POSITIVE LOGITS
     ()
    0.70
     arg
    0.68
     {
    0.66
    arg
    0.65
     p
    0.59
     ary
    0.58
     _
    0.57
    arr
    0.57
    ()
    0.57
     params
    0.56
    Act Density 0.023%

    No Known Activations