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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     அதிகரிக்கிறது
    0.61
     muốn
    0.57
     podían
    0.57
     Objet
    0.57
          
    0.55
     EMPTY
    0.55
     Objects
    0.54
     বক্তব্য
    0.54
     заинтересо
    0.54
     влияет
    0.54
    POSITIVE LOGITS
     Ours
    0.68
    Kle
    0.67
     scars
    0.66
     Romney
    0.66
     Kle
    0.65
     Heide
    0.63
    ទៀត
    0.62
    ToCheck
    0.61
    idega
    0.61
    早速
    0.61
    Act Density 0.000%

    No Known Activations