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

    Neuronpedia

    INDEX
    Explanations

    face masks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    删除
    0.82
    valmentaja
    0.74
    peicher
    0.73
    పాల
    0.71
    iteritems
    0.70
    ើត
    0.69
     انقلاب
    0.69
     प्रॉब्ल
    0.69
    削除
    0.67
     एनालिसिस
    0.67
    POSITIVE LOGITS
     masks
    2.45
     mask
    2.40
     Masks
    2.29
    口罩
    2.07
    Mask
    2.05
     Mask
    2.00
     COVID
    2.00
    masks
    1.94
    mask
    1.93
    マスク
    1.93
    Act Density 0.034%

    No Known Activations