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

    Neuronpedia

    INDEX
    Explanations

    speaking and asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     asserts
    0.44
     достижения
    0.43
     Flags
    0.42
    ▄
    0.40
     creation
    0.39
     oscillators
    0.39
     contrasts
    0.39
     inconsistencies
    0.39
     ноябре
    0.39
    дать
    0.39
    POSITIVE LOGITS
     him
    0.47
     honom
    0.45
     তাকে
    0.43
     jego
    0.43
     прямо
    0.43
    他就
    0.41
     allora
    0.41
     his
    0.41
     Biraz
    0.39
    愿意
    0.39
    Act Density 0.026%

    No Known Activations