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

    Neuronpedia

    INDEX
    Explanations

    model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pudieran
    0.67
    ინი
    0.65
    सायटी
    0.64
     Struktur
    0.63
    YNAMICS
    0.61
    isição
    0.61
     দাবিতে
    0.61
     구조
    0.60
     truth
    0.60
     обработки
    0.59
    POSITIVE LOGITS
     Теперь
    0.90
    Tip
    0.83
    now
    0.78
     теперь
    0.76
     тепер
    0.76
     Ahora
    0.75
    Ahora
    0.75
    痉
    0.73
     ज्यो
    0.73
     McGrath
    0.72
    Act Density 0.039%

    No Known Activations