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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åŃĺåľ¨
    -0.30
    æĸĻ
    -0.29
    ##
    -0.28
    dg
    -0.26
    #{
    -0.26
    èŀºä¸Ŀ
    -0.25
    cm
    -0.24
     verw
    -0.23
    ##↵↵
    -0.23
    çī©æĸĻ
    -0.23
    POSITIVE LOGITS
    iali
    0.28
    backs
    0.25
    iado
    0.25
    iação
    0.24
    ระ
    0.24
     day
    0.24
     Day
    0.24
    ppy
    0.24
    ŀĭ
    0.23
    MUX
    0.23
    Act Density 0.022%

    No Known Activations