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

    Neuronpedia

    INDEX
    Explanations

    password compromised

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     잠
    0.41
    잠
    0.40
    फ
    0.39
    କ୍
    0.38
    족
    0.38
    auta
    0.36
    률
    0.36
    anye
    0.36
    אַ
    0.35
    auche
    0.35
    POSITIVE LOGITS
     भ्रष्टाचार
    0.42
     deoarece
    0.42
     расчет
    0.41
     vì
    0.41
     envisaged
    0.41
     promoção
    0.41
    wärt
    0.40
     क्योंकि
    0.39
     equivalence
    0.39
     o
    0.38
    Act Density 0.009%

    No Known Activations