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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     December
    0.92
     nawet
    0.85
     teaspoons
    0.83
     January
    0.79
    ต้อง
    0.78
     Kembali
    0.76
     ankles
    0.76
    ారని
    0.74
     mathematically
    0.73
     cull
    0.73
    POSITIVE LOGITS
     format
    1.17
    形式
    1.01
    oriented
    0.98
     mode
    0.98
    而非
    0.97
    Với
    0.96
     style
    0.96
    式
    0.95
     형태로
    0.95
     および
    0.94
    Act Density 2.781%

    No Known Activations