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

    Neuronpedia

    INDEX
    Explanations

    multilingual code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    宏
    -0.08
    好像
    -0.07
     thịt
    -0.07
    锑
    -0.07
     Yong
    -0.07
    祜
    -0.07
     Московск
    -0.07
    仡
    -0.07
    مفه
    -0.07
     Ceremony
    -0.07
    POSITIVE LOGITS
    SA
    0.07
     associates
    0.07
     Input
    0.07
    因
    0.07
    rai
    0.07
    如
    0.07
     Booster
    0.06
    ゾ
    0.06
     #%
    0.06
     increase
    0.06
    Act Density 0.006%

    No Known Activations