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

    Neuronpedia

    INDEX
    Explanations

    or similar issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そして
    0.72
    그리고
    0.66
    无数
    0.65
    และการ
    0.65
     важней
    0.62
    ുമുള്ള
    0.59
    Plus
    0.58
    each
    0.58
    Each
    0.57
     каждой
    0.56
    POSITIVE LOGITS
     or
    1.48
     или
    1.39
     atau
    1.38
     ಅಥವಾ
    1.33
    หรือ
    1.26
    或
    1.24
     या
    1.23
     hoặc
    1.22
     یا
    1.20
     veya
    1.19
    Act Density 0.487%

    No Known Activations