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

    Neuronpedia

    INDEX
    Explanations

    enemies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    临
    -0.06
     Sony
    -0.06
     دستی
    -0.06
     iterating
    -0.06
    -0.06
    Ice
    -0.06
    奪
    -0.06
    Instantiate
    -0.06
     momentos
    -0.06
    nickname
    -0.06
    POSITIVE LOGITS
    	can
    0.07
    ¯¯¯¯
    0.06
    -push
    0.06
    =back
    0.06
     novel
    0.06
     erh
    0.06
     wang
    0.06
     dök
    0.06
     voy
    0.06
     каль
    0.06
    Act Density 0.012%

    No Known Activations