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

    Neuronpedia

    INDEX
    Explanations

    all, so much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     absolutamente
    0.48
     EVERY
    0.45
    EVERY
    0.43
     Both
    0.41
     betul
    0.41
     Every
    0.40
     every
    0.40
     ausschließlich
    0.40
     오류
    0.39
    oc
    0.39
    POSITIVE LOGITS
     all
    1.04
    这么多
    0.87
     все
    0.80
     banyaknya
    0.79
    那么多
    0.78
     столько
    0.77
     tanta
    0.77
     এত
    0.74
     इतने
    0.73
     tantas
    0.72
    Act Density 0.017%

    No Known Activations