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

    Neuronpedia

    INDEX
    Explanations

    fn, protected, void, new, On, show

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bekannten
    0.67
     budou
    0.64
     svega
    0.58
     deinem
    0.57
     বিশ্বের
    0.57
     бола
    0.57
    ี
    0.56
    ISIONS
    0.55
     sizin
    0.55
    णार्‍या
    0.55
    POSITIVE LOGITS
    ل
    0.68
    น
    0.65
    נ
    0.64
    کم
    0.59
    л
    0.57
    चारी
    0.56
    0.55
    मि
    0.53
     protective
    0.52
    ňuje
    0.52
    Act Density 0.014%

    No Known Activations