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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    刍
    0.58
    াসন
    0.55
     আত্মসমর্পণ
    0.53
     scă
    0.52
    рто
    0.50
    மன்ற
    0.49
    േറ്റ
    0.49
    পন্থ
    0.49
     pptd
    0.48
    াবন
    0.48
    POSITIVE LOGITS
     working
    4.99
     worked
    4.88
    working
    4.76
     works
    4.75
    Working
    4.61
     Working
    4.60
    worked
    4.50
     WORKING
    4.48
     Works
    4.46
     Worked
    4.39
    Act Density 2.368%

    No Known Activations