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

    Neuronpedia

    INDEX
    Explanations

    foreign words and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कल
    0.44
    ُر
    0.44
    ुन
    0.42
    ιού
    0.41
    UGIN
    0.40
     вашу
    0.40
    西安
    0.40
    вут
    0.40
     tadi
    0.40
    लास
    0.40
    POSITIVE LOGITS
    Vict
    0.53
     ويك
    0.52
     تط
    0.46
    ഭ്യാസ
    0.46
     zám
    0.45
     அழு
    0.45
     لازم
    0.44
     اكت
    0.44
    reste
    0.43
     pou
    0.43
    Act Density 0.003%

    No Known Activations