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

    Neuronpedia

    INDEX
    Explanations

    Parentheses/periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BufferedWriter
    -0.07
     clarity
    -0.07
    電視
    -0.07
    内心的
    -0.07
     villain
    -0.06
    基本面
    -0.06
     Screen
    -0.06
    ți
    -0.06
    工匠
    -0.06
    splash
    -0.06
    POSITIVE LOGITS
    聘请
    0.07
    _*
    0.07
    一家
    0.07
     specifies
    0.07
     הא
    0.06
    땸
    0.06
    Æ
    0.06
    pragma
    0.06
    飞船
    0.06
     intervention
    0.06
    Act Density 0.006%

    No Known Activations