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

    Neuronpedia

    INDEX
    Explanations

    この素晴らしい放送大学これはゾンビ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    嫵
    0.70
     tcpHeader
    0.67
    نګه
    0.62
     sırasında
    0.60
    鸪
    0.60
    𝙙
    0.59
    癀
    0.59
     kullanılan
    0.58
     tartış
    0.58
     reduzir
    0.58
    POSITIVE LOGITS
    お
    0.76
    ・
    0.75
    、
    0.75
    ↵
    0.70
    の
    0.70
    が
    0.66
    で
    0.66
    のお
    0.65
    ア
    0.64
    を
    0.64
    Act Density 0.024%

    No Known Activations