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

    Neuronpedia

    INDEX
    Explanations

    October

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chip
    -0.07
     respons
    -0.07
    產
    -0.07
     sch
    -0.07
    一路上
    -0.07
     liabilities
    -0.07
    场景
    -0.07
    设备
    -0.07
    进步
    -0.07
     Alternatively
    -0.07
    POSITIVE LOGITS
    ($('
    0.08
     представляет
    0.07
    (parseInt
    0.07
    .Hide
    0.07
    铊
    0.07
     Listings
    0.07
     '{$
    0.07
    مجلس
    0.06
     Garc
    0.06
    친
    0.06
    Act Density 0.105%

    No Known Activations