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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chiropr
    -0.07
    Learn
    -0.07
    	temp
    -0.07
    Associate
    -0.07
     giảng
    -0.07
     ment
    -0.07
     Tüm
    -0.07
    ORE
    -0.07
    entar
    -0.07
    ㆍ
    -0.07
    POSITIVE LOGITS
    👞
    0.07
    蜐
    0.07
     cover
    0.07
    (cancel
    0.07
    可
    0.06
    {↵
    0.06
     mouse
    0.06
    哭
    0.06
     dünyan
    0.06
    因為
    0.06
    Act Density 0.031%

    No Known Activations