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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    д
    0.61
     t
    0.55
    ander
    0.54
    ock
    0.54
    ong
    0.52
    uber
    0.52
     Sat
    0.51
    ent
    0.50
    s
    0.50
    ack
    0.50
    POSITIVE LOGITS
     défin
    0.58
     倍
    0.58
     judg
    0.55
     kính
    0.55
     oberen
    0.55
     unteren
    0.54
    Ꮡ
    0.54
     éléments
    0.53
     dólares
    0.53
     presupuesto
    0.52
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.