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

    Neuronpedia

    INDEX
    Explanations

    lists with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /
    0.69
    ,
    0.64
    alar
    0.61
    거나
    0.61
     or
    0.60
    !
    0.59
    id
    0.57
    -
    0.56
    axe
    0.55
    star
    0.54
    POSITIVE LOGITS
     Jeśli
    0.87
     اگر
    0.86
     recomendaciones
    0.85
     Tại
    0.85
    如果
    0.81
    ちなみに
    0.81
     আমরা
    0.78
     However
    0.76
     În
    0.76
     अन्य
    0.75
    Act Density 1.313%

    No Known Activations