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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     засто
    0.44
    佟
    0.44
     Discrete
    0.43
     জানায়
    0.43
     ukon
    0.42
     விகி
    0.42
     renormal
    0.41
     зокрема
    0.41
     Numerical
    0.40
     জানায়
    0.39
    POSITIVE LOGITS
    ের
    0.52
    ки
    0.49
    Would
    0.49
    That
    0.48
    They
    0.48
    전
    0.48
    की
    0.47
    き
    0.47
    uitse
    0.46
    coupled
    0.46
    Act Density 0.004%

    No Known Activations