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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gener
    -0.08
    无疑是
    -0.07
    之意
    -0.07
    .selected
    -0.07
    ⋄
    -0.07
    スマ
    -0.07
     locals
    -0.07
    .CREATE
    -0.07
    within
    -0.07
    臆
    -0.06
    POSITIVE LOGITS
    FW
    0.07
    _female
    0.07
    QU
    0.07
    镰
    0.07
     bookstore
    0.06
    Notice
    0.06
     Dropbox
    0.06
    早餐加盟
    0.06
     Labrador
    0.06
    抬起头
    0.06
    Act Density 0.217%

    No Known Activations