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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    万科
    -0.08
    ilik
    -0.07
    ⛰
    -0.07
    _SELECTION
    -0.07
    👹
    -0.07
    벽
    -0.07
    聿
    -0.07
     Julius
    -0.07
    	i
    -0.07
    獬
    -0.06
    POSITIVE LOGITS
    性的
    0.07
    홰
    0.07
    frequency
    0.06
     Федерации
    0.06
    .Disabled
    0.06
     gif
    0.06
     ranges
    0.06
    ouncements
    0.06
    /interfaces
    0.06
    多年来
    0.06
    Act Density 0.023%

    No Known Activations