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

    Neuronpedia

    INDEX
    Explanations

    ox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阿根廷
    -0.07
     할
    -0.07
     المواطن
    -0.07
     mes
    -0.07
    并不是很
    -0.07
    etine
    -0.07
     Gus
    -0.07
    ality
    -0.07
     Hermione
    -0.06
     china
    -0.06
    POSITIVE LOGITS
     azure
    0.07
    ystal
    0.07
    Foo
    0.07
     Violence
    0.06
    =x
    0.06
    ɕ
    0.06
     منطقة
    0.06
    =(-
    0.06
     групп
    0.06
     BoxDecoration
    0.06
    Act Density 0.002%

    No Known Activations