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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    tera
    -0.07
     Serving
    -0.07
    	resolve
    -0.07
     tí
    -0.07
    鲿
    -0.07
    ceu
    -0.07
    ינטר
    -0.07
    ồi
    -0.06
     incentiv
    -0.06
    roc
    -0.06
    POSITIVE LOGITS
     WK
    0.08
     LX
    0.07
    irthday
    0.07
    BeginInit
    0.07
    破损
    0.07
     изделия
    0.07
     wom
    0.06
     wood
    0.06
    我的
    0.06
    }{$
    0.06
    Act Density 0.001%

    No Known Activations