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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Beginning
    0.98
    otyping
    0.95
     pict
    0.95
    फोल
    0.93
    न्यू
    0.93
     Practically
    0.93
     predecessor
    0.93
    clust
    0.91
    நக
    0.91
    strawberry
    0.90
    POSITIVE LOGITS
    れる
    0.88
    ่น
    0.84
    ทรัพย์
    0.83
    aop
    0.82
     വരു
    0.82
     nadi
    0.82
    ทาน
    0.81
    IsPass
    0.79
     uko
    0.79
    れます
    0.78
    Act Density 0.286%

    No Known Activations