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

    Neuronpedia

    INDEX
    Explanations

    account settings or security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    क
    1.14
     is
    1.13
     into
    1.13
     in
    1.07
     à
    1.05
    or
    1.04
    но
    1.01
     Tasma
    1.01
    ado
    1.00
    ка
    1.00
    POSITIVE LOGITS
    يف
    1.27
     доходов
    1.27
    t
    1.23
    Съ
    1.19
    ات
    1.15
    ري
    1.12
    twitter
    1.10
    يات
    1.09
    Ⴝ
    1.09
    privacy
    1.06
    Act Density 0.095%

    No Known Activations