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

    Neuronpedia

    INDEX
    Explanations

    although

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    发表于
    -0.60
    uanya
    -0.58
     Wikiseite
    -0.55
     TextInputType
    -0.53
    LEncoder
    -0.52
    antaranya
    -0.52
    ChromeDriver
    -0.52
     fó
    -0.51
    libft
    -0.51
     wikipagina
    -0.50
    POSITIVE LOGITS
     насељу
    0.74
     that
    0.60
     we
    0.54
     many
    0.50
    >--}}
    0.50
    InjectAttribute
    0.47
    >-->
    0.46
    RepeatedField
    0.46
     المعيارى
    0.45
    ThemeOverlay
    0.45
    Act Density 0.002%

    No Known Activations