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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     aimed
    0.52
     предназна
    0.48
    มากกว่า
    0.41
     предназначен
    0.41
     রানে
    0.38
     אנחנו
    0.38
     MORE
    0.38
     ನಾವು
    0.38
     saya
    0.37
     mores
    0.37
    POSITIVE LOGITS
     который
    0.77
     التي
    0.75
     που
    0.73
     которые
    0.71
     الذي
    0.70
    Applied
    0.70
     който
    0.68
     които
    0.67
     която
    0.66
     który
    0.65
    Act Density 0.000%

    No Known Activations