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

    Neuronpedia

    INDEX
    Explanations

    expressing belief or assumption

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ам
    0.52
     దాని
    0.48
     系统
    0.47
    滗
    0.46
     ощущения
    0.46
    енты
    0.44
    ాతం
    0.44
    İŞ
    0.44
    ಎಂ
    0.43
     ребенка
    0.43
    POSITIVE LOGITS
    to
    0.70
     essere
    0.70
     to
    0.69
    in
    0.61
     être
    0.59
     be
    0.55
     being
    0.55
    ที่จะ
    0.55
    س
    0.54
    être
    0.54
    Act Density 0.053%

    No Known Activations