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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     LOCAL
    0.52
     journaling
    0.46
     vale
    0.46
     phong
    0.46
     prawa
    0.45
     thôn
    0.45
     nullable
    0.44
     chế
    0.44
    ろしく
    0.44
     ఏద
    0.43
    POSITIVE LOGITS
    ア
    0.58
    Wireless
    0.55
    b
    0.54
    ل
    0.54
    T
    0.53
    パ
    0.53
    W
    0.52
    Tr
    0.51
    Hand
    0.51
    Az
    0.51
    Act Density 0.000%

    No Known Activations