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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Book
    -0.08
     dealt
    -0.07
    sweet
    -0.07
     вік
    -0.07
    icol
    -0.06
    -list
    -0.06
     coop
    -0.06
     quận
    -0.06
     SVC
    -0.06
    лась
    -0.06
    POSITIVE LOGITS
    ่างประเทศ
    0.07
     державного
    0.07
    $I
    0.06
     Kushner
    0.06
    ์ส
    0.06
    ORIA
    0.06
    한
    0.06
    .flags
    0.06
    hus
    0.06
    setProperty
    0.06
    Act Density 0.002%

    No Known Activations