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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    当該
    0.41
     {}",
    0.40
     %@",
    0.39
     `
    0.39
     {}'.
    0.38
    \|$.
    0.38
     {}".
    0.38
    |$.
    0.37
    }]$.
    0.37
    ：
    0.37
    POSITIVE LOGITS
    Opens
    0.46
    <unused1563>
    0.42
     publicités
    0.42
     douleur
    0.41
     ATMs
    0.41
    Исто
    0.41
     большую
    0.40
     révol
    0.40
    ,)
    0.40
    .)
    0.40
    Act Density 5.292%

    No Known Activations