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

    Neuronpedia

    INDEX
    Explanations

    numbers and classifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    암
    0.46
    만원
    0.41
     nad
    0.40
     암
    0.39
    ins
    0.38
    世纪
    0.38
    INS
    0.38
    ylie
    0.38
    urne
    0.37
    舖
    0.37
    POSITIVE LOGITS
    个
    0.95
    個
    0.88
     个
    0.82
     個
    0.70
    㑬
    0.66
     cái
    0.65
    개를
    0.63
    一個
    0.61
    개
    0.60
    㑼
    0.59
    Act Density 0.004%

    No Known Activations