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

    Neuronpedia

    INDEX
    Explanations

    depending on context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يد
    0.45
    綰
    0.44
    এবং
    0.44
    MUL
    0.43
    鉀
    0.42
    遊
    0.41
    ರ್ಮ
    0.40
    туре
    0.40
    學習
    0.40
     ambientes
    0.40
    POSITIVE LOGITS
     coincide
    0.43
     或者
    0.43
     подходя
    0.42
     drizzle
    0.41
     relatively
    0.40
    或者是
    0.40
     Mesopot
    0.40
    😢
    0.39
    😞
    0.39
    detectChanges
    0.39
    Act Density 0.016%

    No Known Activations