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

    Neuronpedia

    INDEX
    Explanations

    ((pattern))

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quarrels
    0.52
     patches
    0.48
    كتب
    0.47
    ン
    0.46
    Chúng
    0.45
     is
    0.45
    +\
    0.45
    Không
    0.44
     υπάρχ
    0.44
    我们
    0.43
    POSITIVE LOGITS
     keseluruhan
    0.47
    座椅
    0.45
     فرض
    0.43
     organisme
    0.40
    डु
    0.39
    迥
    0.39
    接到
    0.38
    लीय
    0.38
     所
    0.38
     pejabat
    0.38
    Act Density 0.007%

    No Known Activations