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

    Neuronpedia

    INDEX
    Explanations

    intensifiersverysuperlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hxx
    0.39
     monopolies
    0.37
     $*$
    0.37
     chhoti
    0.36
    غول
    0.36
     gleiche
    0.36
     тел
    0.36
    خلي
    0.36
     कोणत्याही
    0.36
     வாழ்க்கை
    0.36
    POSITIVE LOGITS
     للغاية
    1.85
     banget
    1.83
     جدا
    1.76
    ísimo
    1.67
     lắm
    1.62
     demais
    1.57
    มากๆ
    1.54
    すぎる
    1.53
    ísim
    1.49
    ísima
    1.48
    Act Density 0.024%

    No Known Activations