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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洞察
    -0.08
    朝阳
    -0.07
    إدارة
    -0.07
    깨
    -0.07
    唼
    -0.07
    _ms
    -0.07
     PMC
    -0.07
    成长为
    -0.06
    ('-',
    -0.06
    >();
↵
    -0.06
    POSITIVE LOGITS
     CONT
    0.08
     answers
    0.07
     emulator
    0.07
     HALF
    0.07
     הפי
    0.07
     anywhere
    0.07
    .Lines
    0.07
    -links
    0.07
    百度
    0.07
     claimed
    0.07
    Act Density 0.035%

    No Known Activations