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

    Neuronpedia

    INDEX
    Explanations

    noble metals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gig
    -0.07
     ################################################
    -0.07
    طن
    -0.07
     çıkt
    -0.07
    ↭
    -0.07
    水面
    -0.07
    .examples
    -0.06
    //----------------------------------------------------------------
    -0.06
    @Web
    -0.06
    	JPanel
    -0.06
    POSITIVE LOGITS
     undertake
    0.07
    创作
    0.07
    叁
    0.07
    Dependencies
    0.07
     sightings
    0.06
    缪
    0.06
    読
    0.06
     Tong
    0.06
    と思っている
    0.06
    濠
    0.06
    Act Density 0.224%

    No Known Activations