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

    Neuronpedia

    INDEX
    Explanations

    Arabic greetings and time questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cria
    1.80
     individuais
    1.60
     forne
    1.52
     necessari
    1.51
     quae
    1.47
     foi
    1.46
     ajud
    1.45
     ជា
    1.42
     kasut
    1.41
     ដែល
    1.40
    POSITIVE LOGITS
     من
    2.49
     أو
    2.49
     إ
    2.42
     في
    2.40
     أ
    2.38
     ل
    2.30
     أن
    2.30
     الأ
    2.30
     لم
    2.29
     هذه
    2.28
    Act Density 0.013%

    No Known Activations