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

    Neuronpedia

    INDEX
    Explanations

    levels and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hacer
    0.44
     productos
    0.43
    లా
    0.41
     পণ্য
    0.41
    conten
    0.40
    фы
    0.39
     शर्मा
    0.38
     Zusammenhang
    0.38
     móviles
    0.38
    обходи
    0.38
    POSITIVE LOGITS
     level
    0.79
    レベル
    0.70
     standstill
    0.64
     úrov
    0.63
     levels
    0.62
     уровня
    0.61
     juncture
    0.60
     impasse
    0.58
     outset
    0.57
     crossroads
    0.57
    Act Density 0.082%

    No Known Activations