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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     kids
    0.52
     adaptación
    0.46
     adaption
    0.45
     çocuğ
    0.45
     adaptation
    0.42
    小孩
    0.42
    綀
    0.42
    子供
    0.41
     بچه
    0.41
     adaptations
    0.39
    POSITIVE LOGITS
     readily
    0.42
    demon
    0.41
    inated
    0.41
     blossoms
    0.41
     sweetly
    0.40
     responded
    0.39
     demonstrate
    0.39
    charted
    0.39
     transfert
    0.39
     approche
    0.38
    Act Density 0.008%

    No Known Activations