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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    🔬
    0.71
     निर्णय
    0.70
    ική
    0.65
    ውነ
    0.65
    𝗝
    0.65
    PEND
    0.64
    ทำงาน
    0.63
    ውነተኛ
    0.62
    𝗟
    0.62
    実際に
    0.62
    POSITIVE LOGITS
     noirâtres
    0.78
     hopefully
    0.76
     posterity
    0.73
     umož
    0.71
     respectively
    0.70
     various
    0.70
     combination
    0.70
     Roboto
    0.70
     denominations
    0.69
     respective
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.