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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Tolkien
    0.97
     meditate
    0.84
     enfo
    0.83
     Einheit
    0.83
     ネイビー
    0.81
    چھے
    0.81
     problemat
    0.80
     nostru
    0.80
     Polity
    0.79
     ら
    0.78
    POSITIVE LOGITS
    ور
    0.79
    ار
    0.75
    ی
    0.74
    स
    0.73
    ही
    0.72
    点
    0.68
    ض
    0.68
    צ
    0.68
    ट
    0.67
    Biggest
    0.66
    Act Density 0.001%

    No Known Activations