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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Kre
    0.42
    ROR
    0.41
    ایا
    0.40
    Kre
    0.40
    hore
    0.39
     রাক
    0.39
    Keb
    0.38
    ज
    0.38
    oleh
    0.38
    Clos
    0.36
    POSITIVE LOGITS
     facial
    0.37
     тоді
    0.36
     invo
    0.35
    facial
    0.35
     shreds
    0.35
     Elsewhere
    0.35
    깅
    0.35
     ইল
    0.34
    ագր
    0.34
     mugs
    0.34
    Act Density 0.000%

    No Known Activations