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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    {\
    -0.07
    tridge
    -0.07
    弹性
    -0.07
     Nylon
    -0.07
    iena
    -0.07
     Netz
    -0.07
     Wolver
    -0.06
    常务
    -0.06
    	font
    -0.06
     dank
    -0.06
    POSITIVE LOGITS
     finances
    0.07
    Criterion
    0.07
     CAST
    0.07
    /fwlink
    0.07
    ,col
    0.07
    oil
    0.07
    ışı
    0.07
    をする
    0.06
    /welcome
    0.06
    その後
    0.06
    Act Density 0.066%

    No Known Activations