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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     normas
    1.03
    󰡔
    1.02
     alteraciones
    1.00
     actualización
    0.96
     revisión
    0.96
     нормы
    0.96
     independencia
    0.95
     regula
    0.95
    <0x1C>
    0.93
     propias
    0.93
    POSITIVE LOGITS
    ist
    0.84
    ী
    0.71
    ম
    0.70
    m
    0.70
     manufacturing
    0.66
    ?
    0.66
    -
    0.64
    说
    0.64
    l
    0.63
    c
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.