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

    Neuronpedia

    INDEX
    Explanations

    there is / isn't

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亮
    0.42
    没有任何
    0.39
    ブ
    0.39
    okie
    0.38
    шк
    0.38
    과는
    0.38
     हैं
    0.38
     Nghi
    0.38
    원은
    0.38
     anywhere
    0.37
    POSITIVE LOGITS
     因為
    0.39
    ölker
    0.38
    ज़ार
    0.38
    ruiter
    0.37
    ₮
    0.36
     bert
    0.36
     saper
    0.36
     iss
    0.36
     サマータイヤ
    0.36
    روز
    0.35
    Act Density 0.003%

    No Known Activations