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

    Neuronpedia

    INDEX
    Explanations

    second largest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дальнейшем
    0.40
     अने
    0.39
     particulières
    0.38
     önces
    0.38
     satisfacer
    0.37
    ন্ধে
    0.37
     Eph
    0.36
     unrival
    0.36
    ໍ່
    0.35
    accoon
    0.35
    POSITIVE LOGITS
    🥈
    0.52
     derrière
    0.49
     second
    0.49
     ثاني
    0.48
    Second
    0.48
    second
    0.48
    ranking
    0.46
     ikinci
    0.46
     xếp
    0.45
    behind
    0.45
    Act Density 0.024%

    No Known Activations