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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ርስ
    0.74
     понима
    0.68
    কর্
    0.68
    จากการ
    0.68
     sytuacji
    0.63
     کھیلتے
    0.63
    ಮಗೆ
    0.63
     Rosen
    0.63
     millón
    0.62
     От
    0.62
    POSITIVE LOGITS
     onto
    2.08
     into
    1.78
     vào
    1.63
    Into
    1.34
    into
    1.28
     Into
    1.27
    onto
    1.25
     върху
    1.23
     इनटू
    1.22
     squarely
    1.15
    Act Density 0.702%

    No Known Activations