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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     informs
    0.45
    performs
    0.42
     intim
    0.42
     performs
    0.41
     bly
    0.41
     explains
    0.41
     wewnętr
    0.41
     bł
    0.41
     admits
    0.40
     internally
    0.40
    POSITIVE LOGITS
     気
    0.43
    "]))
    0.39
     ಹುಡು
    0.39
    ﮕ
    0.39
     बढ़ते
    0.38
     frauen
    0.38
    PLICATION
    0.38
     находя
    0.38
    椙
    0.38
     เลือก
    0.38
    Act Density 0.010%

    No Known Activations