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

    Neuronpedia

    INDEX
    Explanations

    of a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     numele
    0.80
     kondisi
    0.79
     uchun
    0.73
     samma
    0.72
     đổ
    0.70
     adanya
    0.68
     nimi
    0.66
     samme
    0.64
     selben
    0.64
     uniquement
    0.64
    POSITIVE LOGITS
    िता
    0.72
    <0x80>
    0.71
    iance
    0.71
    ीकरण
    0.71
     многих
    0.67
     دوسرے
    0.67
    wiście
    0.66
    ádz
    0.65
    checkBox
    0.64
     پیر
    0.64
    Act Density 0.259%

    No Known Activations