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

    Neuronpedia

    INDEX
    Explanations

    using the word "like"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    时不
    -0.07
    牠
    -0.07
     isa
    -0.07
     Veranst
    -0.07
    饲
    -0.06
     �
    -0.06
    %</
    -0.06
    喔
    -0.06
    秭
    -0.06
     imb
    -0.06
    POSITIVE LOGITS
    rement
    0.07
     crawl
    0.07
    CHK
    0.07
     security
    0.07
    ”).
    0.07
    第
    0.06
    compiled
    0.06
    沈阳
    0.06
    坼
    0.06
    ZA
    0.06
    Act Density 0.195%

    No Known Activations