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

    Neuronpedia

    INDEX
    Explanations

    qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.57
     of
    0.54
    、
    0.52
     only
    0.50
    =
    0.49
    +
    0.49
    ，
    0.47
    $.
    0.46
     Kirby
    0.46
     firstly
    0.46
    POSITIVE LOGITS
     تفصیل
    0.53
    ósitos
    0.47
    薬品
    0.46
     drugih
    0.46
     굉장
    0.46
     entusiasmo
    0.46
    缱
    0.45
    ຜະລິດຕະພັນ
    0.45
    衝撃
    0.45
    फारिश
    0.44
    Act Density 0.081%

    No Known Activations