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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noticeably
    -0.07
    点亮
    -0.06
    SENSOR
    -0.06
    ｠
    -0.06
     beast
    -0.06
    Yang
    -0.06
    _migration
    -0.06
    :'.$
    -0.06
     Result
    -0.06
     angular
    -0.06
    POSITIVE LOGITS
     Civic
    0.07
    껭
    0.07
    portunity
    0.06
    ")
↵
↵
    0.06
    技艺
    0.06
    によって
    0.06
     contrace
    0.06
    wild
    0.06
     Architecture
    0.06
    生活习惯
    0.06
    Act Density 0.004%

    No Known Activations