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

    Neuronpedia

    INDEX
    Explanations

    names of authors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     武田
    0.50
     martial
    0.48
    伱
    0.46
    笑道
    0.43
     Martha
    0.43
     bison
    0.42
     jaune
    0.42
     महेंद्र
    0.41
    貂
    0.41
     Zhang
    0.41
    POSITIVE LOGITS
    薄
    0.57
    顾
    0.55
     Gu
    0.53
    Lu
    0.51
    聿
    0.49
    Fu
    0.49
    Th
    0.49
    Mu
    0.49
    Mo
    0.48
    Thin
    0.46
    Act Density 0.001%

    No Known Activations