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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     इन्होंने
    0.96
     මෙය
    0.89
     இவை
    0.86
     وهذه
    0.85
     här
    0.84
     इनको
    0.82
    今天是
    0.82
     এখানে
    0.79
     здесь
    0.79
     इन्हे
    0.79
    POSITIVE LOGITS
     those
    2.32
    those
    2.23
     Those
    2.20
    Those
    2.13
     đó
    2.00
     itu
    2.00
    That
    1.97
     That
    1.96
    那個
    1.95
     eso
    1.94
    Act Density 1.125%

    No Known Activations