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

    Neuronpedia

    INDEX
    Explanations

    type definition or attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    льник
    0.42
    ার্থীদের
    0.41
     உற
    0.40
    윙
    0.40
     অভিজ্ঞতা
    0.40
    ໃຫ້
    0.39
     pengalaman
    0.39
     ຮ
    0.39
     esperienza
    0.38
     書き
    0.38
    POSITIVE LOGITS
     FU
    0.44
     Gig
    0.38
     perfusion
    0.38
     reforming
    0.38
    治
    0.38
     Dell
    0.38
    FU
    0.37
    Fd
    0.36
     WA
    0.36
     fd
    0.36
    Act Density 0.000%

    No Known Activations