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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ANIEL
    0.39
    Whether
    0.38
    можно
    0.38
     callBack
    0.37
    са
    0.37
     resume
    0.37
    מה
    0.36
    一
    0.36
    чина
    0.35
    素材
    0.35
    POSITIVE LOGITS
     LikeLike
    0.39
    sadquotes
    0.39
     Igu
    0.37
    来讲
    0.36
     Argument
    0.35
    isPresent
    0.35
    aing
    0.35
     Salt
    0.35
     घातक
    0.35
    Ⅶ
    0.35
    Act Density 0.001%

    No Known Activations