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

    Neuronpedia

    INDEX
    Explanations

    existential

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뜀
    -0.08
    该游戏
    -0.07
     рамках
    -0.07
     tripod
    -0.07
    +↵↵
    -0.07
    줴
    -0.07
     modele
    -0.07
     twist
    -0.07
     других
    -0.07
    监狱
    -0.07
    POSITIVE LOGITS
    🗨
    0.08
    .Items
    0.07
    нные
    0.07
     employment
    0.07
    Bottom
    0.07
    .Not
    0.07
    Objects
    0.07
    &gt
    0.07
    价值
    0.07
     public
    0.07
    Act Density 0.001%

    No Known Activations