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

    Neuronpedia

    INDEX
    Explanations

    impl of trait/type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,{
    0.38
    顶
    0.38
    inception
    0.37
    ._
    0.36
     чыныгы
    0.36
    гация
    0.35
    aho
    0.35
     unsh
    0.35
    স্তর
    0.35
    чках
    0.35
    POSITIVE LOGITS
     Runnable
    0.42
    اللي
    0.41
    ValueOf
    0.39
     Comparable
    0.39
     Verse
    0.38
    ẍ
    0.38
    쥴
    0.37
     Estim
    0.37
    arness
    0.36
    getMonth
    0.36
    Act Density 0.024%

    No Known Activations