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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     توی
    0.43
    Ⲁ
    0.41
    ꧂
    0.39
    왑
    0.38
    漂亮
    0.38
    ңа
    0.38
     kicker
    0.37
    혔
    0.37
    ភេទ
    0.36
    🇶
    0.36
    POSITIVE LOGITS
    C
    0.42
    ,
    0.41
     Clinical
    0.39
    Chocolate
    0.38
    iser
    0.37
     chocolate
    0.37
    leta
    0.37
    Clinical
    0.37
    Handler
    0.37
    etl
    0.37
    Act Density 0.001%

    No Known Activations