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

    Neuronpedia

    INDEX
    Explanations

    chapter | raw | Walmart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    有可能
    1.22
    າມາດ
    1.12
    மேலும்
    1.11
    े
    1.11
    các
    1.11
    અમ
    1.09
    tains
    1.08
    Các
    1.07
    あるいは
    1.07
     参数
    1.07
    POSITIVE LOGITS
     получаем
    0.98
     haya
    0.95
     дела
    0.95
     ไหน
    0.94
     spade
    0.90
     уж
    0.90
     dishonest
    0.90
     libel
    0.90
     bianca
    0.90
     hayan
    0.89
    Act Density 0.004%

    No Known Activations