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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tutorial
    -0.08
     Boss
    -0.07
    に入る
    -0.07
     Mosul
    -0.07
    させ
    -0.07
    izar
    -0.06
    CallBack
    -0.06
     yapıyor
    -0.06
    (coord
    -0.06
    出來
    -0.06
    POSITIVE LOGITS
    ╥
    0.06
    凸
    0.06
     wealthy
    0.06
     Pagination
    0.06
    /pay
    0.06
    .='<
    0.06
    ฮอ
    0.06
    .exception
    0.06
     �
    0.06
    ۥ
    0.06
    Act Density 0.081%

    No Known Activations