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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .family
    -0.08
     during
    -0.07
     कर
    -0.07
     puss
    -0.07
     datatype
    -0.07
    "'
    -0.07
    -bound
    -0.07
     powered
    -0.06
    ，不过
    -0.06
    Mis
    -0.06
    POSITIVE LOGITS
    影
    0.06
     М
    0.06
     '@/
    0.06
     แก
    0.06
    (xx
    0.06
    _PC
    0.06
     ремонт
    0.06
    .rightBarButtonItem
    0.06
     skutečnosti
    0.06
     pazar
    0.06
    Act Density 0.000%

    No Known Activations