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

    Neuronpedia

    INDEX
    Explanations

    licenses and details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rx
    -0.07
    十一
    -0.07
     desperation
    -0.07
     maximal
    -0.07
    /inc
    -0.07
    .req
    -0.07
    -Aug
    -0.07
    十四五
    -0.07
    反省
    -0.07
    Tax
    -0.06
    POSITIVE LOGITS
    薮
    0.07
    �
    0.06
    Party
    0.06
    メリ
    0.06
    aisy
    0.06
     사람이
    0.06
    parated
    0.06
     крови
    0.06
    宋体
    0.06
    arie
    0.06
    Act Density 0.018%

    No Known Activations