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

    Neuronpedia

    INDEX
    Explanations

    diverse scripts and languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afflict
    0.47
     मेल
    0.40
    oreo
    0.39
     aiming
    0.38
     selfies
    0.38
     evid
    0.38
     envis
    0.38
     surnames
    0.37
     фонбет
    0.36
     рассматри
    0.36
    POSITIVE LOGITS
    为一个
    0.46
    ້
    0.45
    ៍
    0.44
    рующие
    0.44
    ร้อม
    0.43
    телям
    0.43
     যন্ত্রপাতি
    0.41
    ینو
    0.41
    矵
    0.41
    ्यात
    0.41
    Act Density 0.009%

    No Known Activations