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

    Neuronpedia

    INDEX
    Explanations

    を

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ترین
    -0.06
    sales
    -0.06
    <Car
    -0.06
    難
    -0.06
     FOX
    -0.06
     показ
    -0.06
     rằng
    -0.06
     POS
    -0.06
    nas
    -0.06
     Jin
    -0.06
    POSITIVE LOGITS
    を
    0.14
    를
    0.12
    을
    0.11
     を
    0.11
    」を
    0.10
    )를
    0.10
    자를
    0.10
    위를
    0.10
    ことを
    0.09
    식을
    0.09
    Act Density 0.018%

    No Known Activations