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

    Neuronpedia

    INDEX
    Explanations

    defining rules before existing ad copy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vão
    1.11
    ნიშვნ
    1.05
    ună
    0.99
    sgem
    0.98
     الأ
    0.94
    GlobalSection
    0.92
     njegova
    0.92
     undeni
    0.91
    istent
    0.91
    ⠉
    0.91
    POSITIVE LOGITS
    ين
    1.09
     vassal
    1.06
    ی
    1.05
     Pars
    1.04
    neath
    1.03
    buds
    1.02
     recalls
    1.01
    कतों
    1.01
    hood
    1.00
    beauty
    0.99
    Act Density 0.000%

    No Known Activations