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

    Neuronpedia

    INDEX
    Explanations

    code structure elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    数据
    0.45
     elucid
    0.43
    .³
    0.41
     dados
    0.41
     Iván
    0.41
     IERC
    0.40
    openqa
    0.40
    طيكم
    0.39
     druhé
    0.39
     Ми
    0.39
    POSITIVE LOGITS
     시간에는
    0.55
    })=
    0.49
    and
    0.47
    ord
    0.44
    사는
    0.44
     ແມ່ນ
    0.44
    })=\
    0.43
    นั้น
    0.43
    Z
    0.43
     არის
    0.42
    Act Density 0.021%

    No Known Activations