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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     MAKEINTRESOURCE
    0.96
    不得不
    0.95
    ين
    0.95
     glaub
    0.95
    儅
    0.94
    ់
    0.91
    櫚
    0.91
    นัก
    0.89
    ்ட்
    0.88
    الصفحه
    0.88
    POSITIVE LOGITS
    2
    1.02
    ти
    0.90
    0.90
    7
    0.86
    1
    0.84
    3
    0.84
    4
    0.83
     fuller
    0.82
    5
    0.80
    ğini
    0.76
    Act Density 0.000%

    No Known Activations