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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    คะแน
    -0.07
     McCartney
    -0.07
    ｃ
    -0.07
     kịch
    -0.06
     praised
    -0.06
    	th
    -0.06
    thood
    -0.06
    ADV
    -0.06
    鲜活
    -0.06
    绿茶
    -0.06
    POSITIVE LOGITS
    潮
    0.07
    なの
    0.07
    wap
    0.07
    升级
    0.07
    炮
    0.07
    吼
    0.07
    .comments
    0.07
    上涨
    0.07
    削减
    0.07
    ulação
    0.06
    Act Density 0.274%

    No Known Activations