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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    happiness
    0.68
    ק
    0.66
    தான்
    0.63
     shayari
    0.63
    ak
    0.62
    韓国
    0.59
    isan
    0.59
     sería
    0.58
     morceau
    0.58
    intend
    0.55
    POSITIVE LOGITS
    רים
    0.71
    ваемые
    0.64
     Các
    0.60
    n
    0.55
    ﻌ
    0.54
     various
    0.53
     The
    0.52
    н
    0.50
     피해
    0.50
     பல்வேறு
    0.49
    Act Density 2.122%

    No Known Activations