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

    Neuronpedia

    INDEX
    Explanations

    protective sunglasses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    کن
    0.54
    静
    0.45
    ляют
    0.43
     Bộ
    0.43
    铅
    0.43
    瑁
    0.42
     호출
    0.42
    谚
    0.42
     جمعه
    0.41
    л
    0.41
    POSITIVE LOGITS
    ’
    0.55
    investment
    0.49
     we
    0.48
     Africa
    0.47
    field
    0.47
     retail
    0.46
    purchase
    0.46
     pricing
    0.46
     African
    0.45
    欣賞
    0.45
    Act Density 0.007%

    No Known Activations