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

    Neuronpedia

    INDEX
    Explanations

    Char

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ขาย
    -0.07
     BOOK
    -0.07
     cafe
    -0.06
    .Mock
    -0.06
    nictví
    -0.06
    VERRIDE
    -0.06
     출력
    -0.06
    _dynamic
    -0.06
     altern
    -0.06
    .nextSibling
    -0.06
    POSITIVE LOGITS
    <ul
    0.07
    Play
    0.07
    Watch
    0.06
     ‌
    0.06
    prepare
    0.06
    ovaného
    0.06
    ponsible
    0.06
    重要
    0.06
    Listening
    0.06
    ้น
    0.06
    Act Density 0.006%

    No Known Activations