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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     た
    0.43
    ندہ
    0.43
     December
    0.41
     november
    0.41
     November
    0.40
     January
    0.40
     durante
    0.40
     June
    0.39
     stali
    0.38
     Christmas
    0.37
    POSITIVE LOGITS
     loses
    0.46
     يل
    0.46
    Pays
    0.45
    不
    0.44
    ᱴ
    0.43
     يقوم
    0.43
     promulg
    0.43
     sprayer
    0.43
     یق
    0.42
     אוי
    0.42
    Act Density 0.000%

    No Known Activations