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

    Neuronpedia

    INDEX
    Explanations

    Arabic words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    strates
    0.44
     balas
    0.44
     voces
    0.44
     rails
    0.43
     assumed
    0.41
    xa
    0.41
     joins
    0.41
     mobiles
    0.41
    வலை
    0.41
     hackers
    0.40
    POSITIVE LOGITS
    ئ
    0.43
    ات
    0.41
    multline
    0.39
    ائع
    0.38
     المعد
    0.38
    امل
    0.37
    ﺌ
    0.37
    巷
    0.37
     الدنيا
    0.37
    امج
    0.36
    Act Density 0.003%

    No Known Activations