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

    Neuronpedia

    INDEX
    Explanations

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quette
    -0.07
    赞
    -0.07
     Kitchen
    -0.07
     ****************************************************************
    -0.07
     Mitchell
    -0.07
    etter
    -0.07
     onTap
    -0.07
    振
    -0.07
     Tân
    -0.07
     Moore
    -0.07
    POSITIVE LOGITS
     hard
    0.09
    ⋱
    0.08
     систем
    0.07
    PLIC
    0.07
    )\
    0.07
    發生
    0.07
    /AIDS
    0.07
     размер
    0.07
     tamanho
    0.07
     içinde
    0.06
    Act Density 0.027%

    No Known Activations