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

    Neuronpedia

    INDEX
    Explanations

    size comparisons for places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    芓
    0.64
     использовать
    0.57
    irittura
    0.57
    ចែកចាយ
    0.57
     consiglio
    0.56
     `,
    0.56
     согласно
    0.56
     (${
    0.55
     применять
    0.54
     Россий
    0.54
    POSITIVE LOGITS
    ाइस
    0.59
    ائو
    0.59
     amely
    0.59
    adeloupe
    0.57
    انوں
    0.55
     whos
    0.54
    اؤن
    0.52
    xE
    0.52
     يحت
    0.52
    땠
    0.52
    Act Density 0.007%

    No Known Activations