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

    Neuronpedia

    INDEX
    Explanations

    the slightly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一个
    2.96
     edhe
    2.25
    时间和
    2.19
    小
    2.13
    с
    2.10
     மற்றும்
    2.09
    一个新的
    2.09
     jedoch
    2.09
    м
    2.05
     ώστε
    2.00
    POSITIVE LOGITS
    ंगाबाद
    2.49
     whatnot
    2.42
    rogens
    2.41
     sebagainya
    2.36
     consequently
    2.36
    amp
    2.35
    romeda
    2.33
    quot
    2.32
    蔼
    2.31
    rarr
    2.27
    Act Density 0.543%

    No Known Activations