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

    Neuronpedia

    INDEX
    Explanations

    simple jailbreak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    漅
    0.41
     कं
    0.40
    ző
    0.39
    午
    0.39
    ട്ടം
    0.39
     বছর
    0.38
    ʉ
    0.38
    રો
    0.38
    kang
    0.38
    egy
    0.37
    POSITIVE LOGITS
     Elementary
    0.46
     комплекса
    0.40
     associations
    0.39
     elementary
    0.39
     Список
    0.38
     elems
    0.38
     acerca
    0.38
     stesso
    0.38
     Sì
    0.38
     vues
    0.38
    Act Density 0.000%

    No Known Activations