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

    Neuronpedia

    INDEX
    Explanations

    asking to share

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ched
    1.34
    kode
    1.23
    ገል
    1.16
     المال
    1.15
     Umum
    1.13
     Donations
    1.13
     Editions
    1.12
     Нов
    1.12
    ær
    1.10
     Pioneers
    1.10
    POSITIVE LOGITS
    ли
    1.61
    ر
    1.51
    り
    1.49
    ות
    1.40
    來講
    1.35
    ق
    1.34
     morphism
    1.33
    igkeit
    1.32
    ен
    1.30
    ัน
    1.29
    Act Density 0.000%

    No Known Activations