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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ชื่อ
    0.59
    hbox
    0.56
     goodwill
    0.55
    داشت
    0.54
    onload
    0.54
    صد
    0.54
    щь
    0.53
    рен
    0.52
     fark
    0.52
    自信
    0.52
    POSITIVE LOGITS
     বাস্তবিক
    0.61
     تُ
    0.59
     Material
    0.59
     기능을
    0.58
     greedy
    0.58
     Эль
    0.55
    龙
    0.55
     Comput
    0.55
     Medicinal
    0.55
     那麼
    0.54
    Act Density 0.023%

    No Known Activations