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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alış
    -0.07
    ቡ
    -0.07
    ꙋ
    -0.07
    ided
    -0.07
    的帮助下
    -0.07
     hear
    -0.07
    孥
    -0.07
     persuaded
    -0.07
    躅
    -0.07
    bett
    -0.07
    POSITIVE LOGITS
    гран
    0.09
    棋
    0.07
    schließen
    0.07
    菊
    0.07
     Painting
    0.07
    演艺
    0.07
     khoảng
    0.07
    flower
    0.07
    酱油
    0.06
     umbrella
    0.06
    Act Density 0.021%

    No Known Activations