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

    Neuronpedia

    INDEX
    Explanations

    describes degree followed by purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ίν
    0.43
    こともある
    0.39
    ets
    0.37
     nummer
    0.37
     เหน
    0.37
    Trying
    0.37
    èr
    0.37
    af
    0.36
    𝓷
    0.36
    龙
    0.36
    POSITIVE LOGITS
     để
    0.90
     чтобы
    0.82
     untuk
    0.71
     ώστε
    0.71
     upang
    0.70
     для
    0.68
     να
    0.68
     بحيث
    0.66
    ທີ່ຈະ
    0.66
     لت
    0.65
    Act Density 0.012%

    No Known Activations