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

    Neuronpedia

    INDEX
    Explanations

    penalty shootout

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    1.46
    ю
    1.29
    о
    1.27
    ier
    1.26
    值
    1.25
    ishing
    1.22
    大小
    1.21
    خدام
    1.21
    ous
    1.20
    한
    1.18
    POSITIVE LOGITS
    zare
    1.58
     syscall
    1.53
    aş
    1.50
    a
    1.44
    います
    1.44
     angiography
    1.41
     overriding
    1.41
     stakes
    1.38
    ا
    1.36
     auspicious
    1.34
    Act Density 0.005%

    No Known Activations