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

    Neuronpedia

    INDEX
    Explanations

    rage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xmax
    -0.08
    �
    -0.07
    不良信息
    -0.07
    午餐
    -0.07
    元宝
    -0.07
    �
    -0.07
    渫
    -0.07
    unicip
    -0.07
    촨
    -0.07
    zier
    -0.07
    POSITIVE LOGITS
     hor
    0.07
     joined
    0.07
    包装
    0.07
    _tv
    0.07
    🔴
    0.07
     agitation
    0.06
    _args
    0.06
    _BL
    0.06
     OSX
    0.06
    /{
    0.06
    Act Density 0.143%

    No Known Activations