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

    Neuronpedia

    INDEX
    Explanations

    produces Trio, Respect, rules, shopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ---
    0.71
    ंद
    0.67
    Lieutenant
    0.66
     "
    0.65
    ೋ
    0.65
     тыся
    0.64
    Sage
    0.64
     وزير
    0.63
    $-$,
    0.63
    $',
    0.62
    POSITIVE LOGITS
    罍
    0.88
    鹬
    0.83
     देखेंगे
    0.81
    想法
    0.81
     estimés
    0.77
     ใจ
    0.76
    open
    0.76
     mirada
    0.76
    没人
    0.76
    र्में
    0.75
    Act Density 0.008%

    No Known Activations