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

    Neuronpedia

    INDEX
    Explanations

    ray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Users
    -0.07
     inactive
    -0.07
    (Tree
    -0.07
    不存在
    -0.07
    侠
    -0.07
     getLast
    -0.07
    nk
    -0.07
     ko
    -0.07
    背面
    -0.07
    螈
    -0.07
    POSITIVE LOGITS
     wollen
    0.07
     cancell
    0.06
     marches
    0.06
     pressured
    0.06
     textColor
    0.06
     boiled
    0.06
     wireless
    0.06
    燃油
    0.06
    ultiply
    0.06
     Engl
    0.06
    Act Density 0.005%

    No Known Activations