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

    Neuronpedia

    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sortOrder
    -0.07
    бе
    -0.07
    Uri
    -0.06
    orang
    -0.06
     vieille
    -0.06
     certo
    -0.06
    is
    -0.06
     is
    -0.06
    罗斯
    -0.06
    369
    -0.06
    POSITIVE LOGITS
    security
    0.07
     처리
    0.07
     russian
    0.07
     Efficiency
    0.06
    ;/
    0.06
     خرد
    0.06
     "@/
    0.06
    iệt
    0.06
     Laboratories
    0.06
    .Mod
    0.06
    Act Density 0.092%

    No Known Activations