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

    Neuronpedia

    INDEX
    Explanations

    string processing code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    (mark
    -0.07
     Phụ
    -0.07
    דא
    -0.07
     Preston
    -0.07
     LAP
    -0.07
    课程
    -0.07
    _missing
    -0.07
     att
    -0.07
     [:
    -0.07
    POSITIVE LOGITS
    enumer
    0.08
    uvian
    0.07
    🅱
    0.07
    inflate
    0.07
    _emlrt
    0.07
    (letter
    0.07
     burned
    0.07
    一等奖
    0.07
     التنفيذي
    0.06
    谧
    0.06
    Act Density 0.105%

    No Known Activations