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

    Neuronpedia

    INDEX
    Explanations

    button

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achts
    -0.07
     tomato
    -0.07
     stationary
    -0.07
     Republic
    -0.07
     redistribution
    -0.07
     coff
    -0.06
    Comput
    -0.06
    Porn
    -0.06
     Marvin
    -0.06
     Wig
    -0.06
    POSITIVE LOGITS
    ・・・↵↵
    0.07
     unlock
    0.07
    结构
    0.07
    ест
    0.06
    第一次
    0.06
    >>();↵↵
    0.06
    (express
    0.06
     σελ
    0.06
     indifferent
    0.06
     countdown
    0.06
    Act Density 0.003%

    No Known Activations