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

    Neuronpedia

    INDEX
    Explanations

    create/make

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    церт
    0.57
    UAGES
    0.57
     নীর
    0.57
     অধর
    0.55
     denominada
    0.55
    ويات
    0.55
    купно
    0.54
    اليد
    0.54
    войства
    0.54
     privind
    0.54
    POSITIVE LOGITS
     manufactured
    0.63
     produced
    0.61
     fabricated
    0.61
     Assumption
    0.59
    ریشن
    0.55
     implemented
    0.54
     generated
    0.53
     Manufactured
    0.52
     over
    0.52
     created
    0.52
    Act Density 0.000%

    No Known Activations