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

    Neuronpedia

    INDEX
    Explanations

    probabilities and specific scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ro
    1.81
    on
    1.67
     jaar
    1.56
    ة
    1.50
     ounces
    1.47
    rije
    1.41
    ië
    1.40
    isier
    1.37
     steep
    1.34
    cado
    1.32
    POSITIVE LOGITS
    عرض
    1.74
    ंना
    1.71
    चुरल
    1.68
     المستقيم
    1.64
    િક
    1.62
    وامی
    1.62
     requisitos
    1.62
    س
    1.57
    ديد
    1.53
     grava
    1.52
    Act Density 0.000%

    No Known Activations