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

    Neuronpedia

    INDEX
    Explanations

    Come

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    儿科
    -0.07
    修饰
    -0.07
     prepare
    -0.07
    下一步
    -0.06
     overturned
    -0.06
    ewis
    -0.06
     besch
    -0.06
    ʦ
    -0.06
    -error
    -0.06
    芦
    -0.06
    POSITIVE LOGITS
    一點
    0.07
    小编一起
    0.07
     Goat
    0.07
    變得
    0.06
    _Port
    0.06
    بول
    0.06
    (sentence
    0.06
    꽁
    0.06
    �
    0.06
    玩具
    0.06
    Act Density 0.078%

    No Known Activations