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

    Neuronpedia

    INDEX
    Explanations

    Bee

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سف
    -0.06
     It
    -0.06
     insider
    -0.06
     whats
    -0.06
    Thêm
    -0.06
    _position
    -0.06
    通常
    -0.06
     Billboard
    -0.06
     goose
    -0.06
     dialogs
    -0.06
    POSITIVE LOGITS
    νά
    0.07
    ="{{
    0.07
    -Allow
    0.07
     imagen
    0.07
     ['$
    0.06
    ฤษภาคม
    0.06
    ="'.$
    0.06
    iki
    0.06
     JADX
    0.06
     เจ
    0.06
    Act Density 0.119%

    No Known Activations