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

    Neuronpedia

    INDEX
    Explanations

    say "the" or "a"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    加班
    -0.07
    骄
    -0.07
    .nickname
    -0.07
    캡
    -0.07
     nap
    -0.06
    -notes
    -0.06
    @author
    -0.06
    郦
    -0.06
    竣工
    -0.06
    -upload
    -0.06
    POSITIVE LOGITS
    ANDOM
    0.07
    全局
    0.06
    bane
    0.06
    информ
    0.06
    經驗
    0.06
    Bounding
    0.06
     Erect
    0.06
    ÜN
    0.06
     HPV
    0.06
     ogs
    0.06
    Act Density 0.002%

    No Known Activations