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

    Neuronpedia

    INDEX
    Explanations

    abstract qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nhàng
    0.69
     ۳
    0.68
     vraie
    0.66
     ಗೊತ್ತ
    0.64
     이날
    0.63
     県
    0.63
     ቦታ
    0.62
     ෆ
    0.62
     ljudi
    0.61
     ٣
    0.61
    POSITIVE LOGITS
    2
    1.24
    '
    1.01
    8
    0.93
    在
    0.89
    ig
    0.86
     in
    0.84
    ↵
    0.84
     are
    0.83
    1
    0.82
    6
    0.82
    Act Density 0.045%

    No Known Activations