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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    いた
    0.74
    皆様
    0.59
     وكانت
    0.59
    ℝ
    0.58
    𝗛
    0.58
    서
    0.57
    🤗
    0.57
    😍
    0.56
    0.56
    娀
    0.56
    POSITIVE LOGITS
    ة
    0.73
    ل
    0.66
    cknowled
    0.65
    el
    0.63
    ной
    0.63
    на
    0.63
    ان
    0.61
    ер
    0.61
     moisturizing
    0.61
    es
    0.59
    Act Density 15.146%

    No Known Activations