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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    觖
    -0.07
    Small
    -0.07
     labeled
    -0.07
    aji
    -0.07
     insist
    -0.07
    此处
    -0.07
    tega
    -0.07
    不知
    -0.06
    cla
    -0.06
    rasing
    -0.06
    POSITIVE LOGITS
    (Media
    0.07
    ()));
    0.06
    Orientation
    0.06
     DID
    0.06
    :param
    0.06
    ーション
    0.06
    )&
    0.06
    东盟
    0.06
    த
    0.06
     documentary
    0.06
    Act Density 0.000%

    No Known Activations