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

    Neuronpedia

    INDEX
    Explanations

    help you with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )،
    0.38
    "،
    0.35
     технологии
    0.33
     কালের
    0.32
     である
    0.32
     wpły
    0.32
    是怎么
    0.31
     JSON
    0.31
    )，
    0.31
    独特的
    0.31
    POSITIVE LOGITS
     him
    0.52
     you
    0.48
     them
    0.46
     đỡ
    0.45
    ia
    0.44
    你
    0.44
     to
    0.41
     আপনাকে
    0.40
    ین
    0.39
    khane
    0.39
    Act Density 0.067%

    No Known Activations