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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    𝙠
    1.13
    Ін
    0.96
    до
    0.95
    蒨
    0.95
    dul
    0.91
    дома
    0.88
    Для
    0.87
     זה
    0.86
    clerosis
    0.86
    don
    0.86
    POSITIVE LOGITS
     unharmed
    0.90
     wichtigen
    0.89
    })(\
    0.86
     th
    0.83
     briefly
    0.82
    roxine
    0.82
     oncoming
    0.81
    稱
    0.80
    ت
    0.80
     optimized
    0.80
    Act Density 0.011%

    No Known Activations