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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Gu
    0.67
    Mars
    0.66
    Pir
    0.64
    Parad
    0.64
    Flight
    0.62
    FLICT
    0.61
    Parent
    0.61
     unrelated
    0.60
    ⌥
    0.60
    Plant
    0.60
    POSITIVE LOGITS
    就是一个
    0.79
     একটা
    0.73
     ფუნქ
    0.71
    是一种
    0.70
     इसका
    0.67
    इसका
    0.65
     प्रणाली
    0.63
    这种
    0.62
    を採用
    0.61
    ilyl
    0.61
    Act Density 0.000%

    No Known Activations