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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Americans
    0.93
     Citizens
    0.92
     определя
    0.87
    堬
    0.86
    QRSTUVWXYZ
    0.86
     citizenship
    0.85
    мерикан
    0.85
    amesh
    0.84
     обраща
    0.84
    ούν
    0.83
    POSITIVE LOGITS
    lier
    1.01
    CC
    1.00
    breaker
    0.98
     unica
    0.96
     unico
    0.96
    illier
    0.96
     khắc
    0.93
    үкт
    0.93
    Ꮜ
    0.93
    Clearly
    0.93
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.