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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     individual
    -0.07
    ᵒ
    -0.07
    贵金属
    -0.07
    驽
    -0.07
     desc
    -0.07
     rub
    -0.06
    游戏角色
    -0.06
    �
    -0.06
     medieval
    -0.06
     Agile
    -0.06
    POSITIVE LOGITS
     burnt
    0.08
    皇上
    0.07
    otton
    0.07
    用力
    0.07
    rawer
    0.07
    小さな
    0.07
    �
    0.07
    掛
    0.07
    holes
    0.07
    떤
    0.07
    Act Density 0.006%

    No Known Activations