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

    Neuronpedia

    INDEX
    Explanations

    one of the most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     или
    0.53
     hoặc
    0.52
     அல்லது
    0.52
    หรือ
    0.49
    或
    0.49
     atau
    0.46
    または
    0.46
     లేదా
    0.44
     ಅಥವಾ
    0.43
     અથવા
    0.42
    POSITIVE LOGITS
     those
    0.82
     ceux
    0.64
    Those
    0.63
    those
    0.63
     những
    0.63
     самых
    0.63
    那些
    0.62
     Those
    0.61
     těch
    0.61
     thoſe
    0.59
    Act Density 0.006%

    No Known Activations