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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     об
    0.87
     twigs
    0.86
     Trauma
    0.84
    roasted
    0.84
    バンド
    0.84
     Line
    0.82
    Line
    0.81
     Tone
    0.79
     দাদা
    0.79
     切り
    0.78
    POSITIVE LOGITS
    /**
    0.79
    /*
    0.79
     einge
    0.73
    <?
    0.73
     ray
    0.68
    这件事
    0.68
    uously
    0.68
     সম্বন্ধে
    0.67
    ablemente
    0.67
     consum
    0.66
    Act Density 4.471%

    No Known Activations