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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     imaju
    0.95
     hauptsächlich
    0.94
    ร้อม
    0.92
     riječi
    0.91
     komplet
    0.91
     definiert
    0.90
     beliebt
    0.85
    kých
    0.84
     također
    0.84
     vollständig
    0.83
    POSITIVE LOGITS
    conten
    0.77
     C
    0.75
     A
    0.74
     V
    0.74
     egg
    0.71
    他
    0.70
     R
    0.69
     egli
    0.69
    מ
    0.69
     Egg
    0.68
    Act Density 0.000%

    No Known Activations