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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    रांत
    0.46
     ისინი
    0.44
     there
    0.43
    톈
    0.42
     まし
    0.41
    rchen
    0.41
    逭
    0.40
    PLO
    0.40
     ราช
    0.40
     Tibet
    0.39
    POSITIVE LOGITS
     aggravate
    0.38
    jum
    0.37
    im
    0.36
    igm
    0.35
    oss
    0.34
    xp
    0.34
    ર્ગ
    0.34
    ὀ
    0.34
    ibs
    0.33
    ஸ்ரீ
    0.33
    Act Density 0.002%

    No Known Activations