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

    Neuronpedia

    INDEX
    Explanations

    com

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    categoryId
    -0.07
    んじゃない
    -0.07
    涤
    -0.07
     goat
    -0.07
    	GameObject
    -0.07
    捋
    -0.06
     flee
    -0.06
     isIn
    -0.06
    닐
    -0.06
    تحميل
    -0.06
    POSITIVE LOGITS
    满意度
    0.08
    _party
    0.08
    设
    0.07
     Ком
    0.07
    美的
    0.07
    аб
    0.07
    Including
    0.07
     humor
    0.07
    Security
    0.07
    의
    0.07
    Act Density 0.001%

    No Known Activations