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

    Neuronpedia

    INDEX
    Explanations

    ending services, contracts, or relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Архивная
    0.43
    ના
    0.42
     が
    0.42
    、
    0.41
     Каждый
    0.40
     Когда
    0.38
     Пользова
    0.38
     で
    0.38
     Бо
    0.38
     Про
    0.37
    POSITIVE LOGITS
    ق
    0.42
    in
    0.38
    ك
    0.37
    상
    0.36
    وف
    0.35
     annen
    0.35
    را
    0.34
     Avenger
    0.34
    σε
    0.34
    ми
    0.34
    Act Density 0.042%

    No Known Activations