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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     COP
    1.04
     EC
    1.03
    zev
    0.99
    秣
    0.99
     Verkehrs
    0.98
    uten
    0.98
    빅
    0.98
     synthet
    0.97
     equivariant
    0.96
    耦合
    0.95
    POSITIVE LOGITS
     nephews
    1.95
     nephew
    1.94
    侄
    1.93
    甥
    1.83
     родствен
    1.82
     grandparents
    1.80
     uncles
    1.80
     nieces
    1.76
     fratello
    1.72
    奶奶
    1.72
    Act Density 0.448%

    No Known Activations