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

    Neuronpedia

    INDEX
    Explanations

    document formatting and graph properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cheating
    0.40
     методов
    0.40
     automating
    0.40
     метод
    0.40
    只限平日
    0.40
     Approve
    0.39
    <unused1047>
    0.39
    ოლოგი
    0.39
     விநாயக
    0.39
    దా
    0.38
    POSITIVE LOGITS
    GD
    0.36
    境
    0.34
    yst
    0.34
    ATC
    0.34
    ines
    0.33
     accent
    0.33
     =
    0.32
     worden
    0.32
    V
    0.32
    alla
    0.32
    Act Density 0.002%

    No Known Activations