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

    Neuronpedia

    INDEX
    Explanations

    numbers and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.64
    لق
    0.57
    ى
    0.55
    ون
    0.54
    نق
    0.52
    ف
    0.52
    وم
    0.51
    ા
    0.51
    اد
    0.51
     Ergebnis
    0.51
    POSITIVE LOGITS
     세포
    0.57
    FileDialog
    0.54
    vertex
    0.53
    r
    0.52
    ISSU
    0.51
    vitro
    0.50
    oe
    0.50
    ˜</
    0.49
    cuador
    0.49
    ded
    0.49
    Act Density 0.198%

    No Known Activations