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

    Neuronpedia

    INDEX
    Explanations

    immediate guess

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للع
    0.78
    因
    0.78
     Ernährung
    0.73
    Growing
    0.70
     selama
    0.70
    暖
    0.70
    nem
    0.69
    长期
    0.69
     مراکز
    0.68
     لمدة
    0.68
    POSITIVE LOGITS
     immediately
    0.80
     imme
    0.76
     아
    0.76
     instantly
    0.75
     immediate
    0.75
     इंटेल
    0.71
     more
    0.71
     즉
    0.71
     IMMEDI
    0.70
     !!!
    0.68
    Act Density 1.832%

    No Known Activations