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

    Neuronpedia

    INDEX
    Explanations

    Native American removal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skulle
    -0.07
    假设
    -0.07
     ít
    -0.07
    到现在
    -0.07
     mav
    -0.07
     focused
    -0.07
    -j
    -0.07
    עוב
    -0.07
     ];
↵
    -0.07
     agli
    -0.07
    POSITIVE LOGITS
     exquisite
    0.07
    睡眠
    0.07
    Requirement
    0.07
    undy
    0.07
     הטבע
    0.06
    옙
    0.06
    влекательн
    0.06
    貅
    0.06
    )._
    0.06
    ElementsByTagName
    0.06
    Act Density 0.010%

    No Known Activations