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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rosso
    -0.07
    ented
    -0.07
     generosity
    -0.07
    ghest
    -0.07
     occ
    -0.07
     vô
    -0.06
    ÓN
    -0.06
    raises
    -0.06
    _coin
    -0.06
    issuer
    -0.06
    POSITIVE LOGITS
     пуст
    0.13
     Nokia
    0.10
     компании
    0.06
    Sizer
    0.06
     díky
    0.06
    ":["
    0.06
    ，从
    0.06
    eldorf
    0.06
     тверд
    0.06
    oz
    0.06
    Act Density 0.003%

    No Known Activations