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

    Neuronpedia

    INDEX
    Explanations

    Legal disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拥抱
    -0.07
     Plugin
    -0.07
    (ws
    -0.07
     adipisicing
    -0.07
     kindly
    -0.07
     ApiException
    -0.07
    <?↵
    -0.07
    ừ
    -0.07
     chàng
    -0.07
    龙湖
    -0.07
    POSITIVE LOGITS
    /al
    0.07
    灵活性
    0.07
     downward
    0.06
    .actual
    0.06
    لب
    0.06
    Tar
    0.06
    netinet
    0.06
     bệnh
    0.06
    重中之重
    0.06
    אוכל
    0.06
    Act Density 0.001%

    No Known Activations