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

    Neuronpedia

    INDEX
    Explanations

    C

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polished
    -0.07
    اذ
    -0.06
    ليات
    -0.06
    ether
    -0.06
    τικής
    -0.06
    egin
    -0.06
    ्वव
    -0.06
    ná
    -0.06
    düğ
    -0.06
     polish
    -0.06
    POSITIVE LOGITS
     Все
    0.08
     giveaways
    0.07
     Sey
    0.07
     Pars
    0.07
    .INVISIBLE
    0.06
    Jul
    0.06
     nuances
    0.06
     Pattern
    0.06
    oz
    0.06
    (class
    0.06
    Act Density 0.016%

    No Known Activations