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

    Neuronpedia

    INDEX
    Explanations

    all, entire, everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     പോലുള്ള
    0.82
    比較的
    0.76
     eher
    0.73
    خرى
    0.71
    前者
    0.71
     บ้าง
    0.67
     דו
    0.67
     주로
    0.64
     spesso
    0.64
     เงี้ย
    0.63
    POSITIVE LOGITS
     all
    5.74
     semua
    5.56
     всех
    5.24
     todas
    5.07
     всички
    4.93
     모든
    4.86
     جميع
    4.85
    すべての
    4.84
     tutte
    4.80
     всіх
    4.77
    Act Density 1.833%

    No Known Activations