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

    Neuronpedia

    INDEX
    Explanations

    absence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पश्चात
    0.45
     अथवा
    0.43
     אך
    0.42
     &/
    0.42
     혹은
    0.42
     Veuillez
    0.40
     deberá
    0.40
     हेतु
    0.39
     deverá
    0.39
     다음과
    0.39
    POSITIVE LOGITS
     really
    0.57
     veldig
    0.55
     ahorita
    0.54
     people
    0.52
    really
    0.49
    いろんな
    0.49
    すごく
    0.49
     لوگوں
    0.48
    people
    0.48
     এটা
    0.48
    Act Density 0.009%

    No Known Activations