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

    Neuronpedia

    INDEX
    Explanations

    writing instructions or patterns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     planta
    0.51
    网红
    0.49
    .​
    0.48
    fron
    0.45
    可以说是
    0.45
    itin
    0.44
    BIG
    0.43
     presentó
    0.43
     Grammy
    0.43
    ريكا
    0.43
    POSITIVE LOGITS
    ウ
    0.47
    䟺
    0.46
    ップ
    0.43
    㿟
    0.43
    㛲
    0.43
    リ
    0.42
    ிகள்
    0.42
    |^{-
    0.41
    㖑
    0.41
    砶
    0.41
    Act Density 0.006%

    No Known Activations