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

    Neuronpedia

    INDEX
    Explanations

    definitions and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dàng
    -0.08
     настоя
    -0.08
     одновременно
    -0.08
     дог
    -0.08
     Сир
    -0.08
     noh
    -0.08
    НЕ
    -0.08
     fällt
    -0.08
     سکے
    -0.08
     bude
    -0.08
    POSITIVE LOGITS
    是什么意思
    0.12
     vs
    0.11
    とは
    0.10
    brief
    0.10
     چیست
    0.09
     versus
    0.09
     Explained
    0.09
    Brief
    0.09
    简介
    0.09
    નો
    0.09
    Act Density 0.166%

    No Known Activations