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

    Neuronpedia

    INDEX
    Explanations

    quoted speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฟอร
    -0.07
    ку
    -0.06
    	temp
    -0.06
    orderBy
    -0.06
    ाब
    -0.06
    -chart
    -0.06
    $num
    -0.06
    lish
    -0.06
     shitty
    -0.06
    提出
    -0.06
    POSITIVE LOGITS
    주시
    0.08
    /em
    0.07
    _AA
    0.07
     athleticism
    0.06
    earing
    0.06
     lawy
    0.06
     WOW
    0.06
    essay
    0.06
    _LINEAR
    0.06
     Bi
    0.06
    Act Density 0.111%

    No Known Activations