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

    Neuronpedia

    INDEX
    Explanations

    at the heart of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     দেয়নি
    0.43
     Reduces
    0.40
     ذریع
    0.39
    ons
    0.39
     verhindern
    0.38
    rys
    0.38
     minded
    0.38
     વખત
    0.38
    fik
    0.37
    mathrm
    0.36
    POSITIVE LOGITS
     terdapat
    1.27
     lies
    1.05
     রয়েছে
    1.04
     есть
    0.97
     রয়েছে
    0.97
     يوجد
    0.95
     υπάρχει
    0.94
     находятся
    0.93
     znajduje
    0.93
     лежит
    0.93
    Act Density 0.013%

    No Known Activations