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

    Neuronpedia

    INDEX
    Explanations

    mouseover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zwischen
    -0.08
    贳
    -0.07
    .cljs
    -0.07
    Registro
    -0.07
     отно
    -0.07
    调动
    -0.07
    (repo
    -0.07
    克思
    -0.07
     Veteran
    -0.07
    处在
    -0.07
    POSITIVE LOGITS
    皇
    0.07
    aaa
    0.07
    QUEUE
    0.07
     proj
    0.07
    Reusable
    0.07
     �
    0.06
    рит
    0.06
    u
    0.06
    alled
    0.06
     erm
    0.06
    Act Density 0.003%

    No Known Activations