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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    unted
    0.99
    ड़ियों
    0.86
    ussel
    0.85
    ۓ
    0.84
     jedna
    0.83
    デニム
    0.83
     układ
    0.82
     clasificación
    0.81
     jaane
    0.81
    tyw
    0.80
    POSITIVE LOGITS
    ر
    0.94
    ৃ
    0.77
    ব
    0.76
    রা
    0.73
    പ്
    0.73
    न
    0.72
     sheer
    0.71
    ല
    0.68
    ع
    0.68
    র
    0.67
    Act Density 0.001%

    No Known Activations