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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ruz
    2.07
    함을
    2.00
    ਊ
    1.98
    ות
    1.91
    말로
    1.89
     않았
    1.89
    ্যে
    1.88
     chiếm
    1.85
    sett
    1.85
    𝓊
    1.83
    POSITIVE LOGITS
    ी
    2.95
    duled
    2.90
    nobyl
    2.83
    此之外
    2.69
    itability
    2.65
    dır
    2.59
    ാ
    2.57
    ామ
    2.57
    ӡ
    2.56
    ea
    2.54
    Act Density 0.239%

    No Known Activations