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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     associée
    0.47
     interventions
    0.42
    लया
    0.41
    δευ
    0.41
     መጠ
    0.41
     staff
    0.40
    പ്പിച്ച
    0.40
    હન
    0.40
    氘
    0.40
     asker
    0.39
    POSITIVE LOGITS
     Pavlov
    0.46
     Escal
    0.43
     Segu
    0.42
         
    0.40
     ninguno
    0.40
             
    0.39
     Hola
    0.39
    BAY
    0.39
     sque
    0.38
    Cuando
    0.38
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.