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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     website
    0.50
     منتشر
    0.49
     recruited
    0.46
     dropped
    0.45
     celebrate
    0.45
    preventDefault
    0.43
     تعالى
    0.42
     clot
    0.42
     digestive
    0.42
     digested
    0.42
    POSITIVE LOGITS
     agosto
    0.63
    ás
    0.57
    ة
    0.57
     கிரே
    0.55
    ż
    0.54
    uari
    0.53
     emocional
    0.52
    し
    0.52
     obras
    0.52
     ಬಾ
    0.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.