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

    Neuronpedia

    INDEX
    Explanations

    Career descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     于
    -0.06
    )size
    -0.06
    oplayer
    -0.06
    (notification
    -0.06
     Live
    -0.06
    .JFrame
    -0.06
     Vari
    -0.06
    .Dir
    -0.06
     діяльності
    -0.06
     afforded
    -0.06
    POSITIVE LOGITS
    	group
    0.07
    appa
    0.07
    Half
    0.06
    姓名
    0.06
    upid
    0.06
     socialist
    0.06
    >This
    0.06
     simplement
    0.06
    adf
    0.06
    oked
    0.06
    Act Density 0.022%

    No Known Activations