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

    Neuronpedia

    INDEX
    Explanations

    Affluent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কিছু
    0.32
     estrategias
    0.32
     باستخدام
    0.31
    利
    0.30
    让他
    0.30
    每次
    0.30
    哪些
    0.29
    自己
    0.29
     ہمیشہ
    0.29
    you
    0.28
    POSITIVE LOGITS
    the
    0.44
    A
    0.44
    O
    0.44
     and
    0.42
    are
    0.41
    ing
    0.38
    G
    0.38
    and
    0.37
    D
    0.36
    T
    0.36
    Act Density 1.951%

    No Known Activations