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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chron
    -0.06
    ляем
    -0.06
    등록
    -0.06
    279
    -0.06
     policeman
    -0.06
    _RESOURCES
    -0.06
     Defender
    -0.06
     Masks
    -0.06
     Кроме
    -0.06
    _Dep
    -0.06
    POSITIVE LOGITS
     kepada
    0.07
    اهی
    0.06
     meddling
    0.06
    (pb
    0.06
    叶
    0.06
     بالا
    0.06
    tığ
    0.06
     زیاد
    0.06
     Dagger
    0.06
    riage
    0.06
    Act Density 0.038%

    No Known Activations