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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    躅
    -0.07
    金牌
    -0.07
    _sensor
    -0.07
     SHOP
    -0.07
    樱花
    -0.07
     intervening
    -0.06
    Wake
    -0.06
    更有
    -0.06
    骕
    -0.06
     `${
    -0.06
    POSITIVE LOGITS
     pleasure
    0.06
     Analy
    0.06
    整齐
    0.06
    légi
    0.06
    沈阳
    0.06
    FLICT
    0.06
    промыш
    0.06
    ()+"
    0.06
    用地
    0.06
     criticize
    0.06
    Act Density 0.102%

    No Known Activations