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

    Neuronpedia

    INDEX
    Explanations

    URLs and image extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    unread
    -0.07
    Deque
    -0.07
    UPDATE
    -0.06
    -actions
    -0.06
     neg
    -0.06
    Bag
    -0.06
    .End
    -0.06
    036
    -0.06
    ابر
    -0.06
    _broadcast
    -0.06
    POSITIVE LOGITS
     dítě
    0.06
    783
    0.06
     ];
    0.06
     cocktail
    0.06
    .swing
    0.06
     작
    0.06
     обеспеч
    0.06
    ように
    0.06
    евер
    0.06
    下的
    0.06
    Act Density 0.008%

    No Known Activations