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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rihanna
    -0.06
     ate
    -0.06
     loneliness
    -0.06
    unpack
    -0.06
    �
    -0.06
    	Title
    -0.06
    .item
    -0.06
    .Import
    -0.06
    oldown
    -0.06
    fund
    -0.06
    POSITIVE LOGITS
     گذاری
    0.07
     اطلاع
    0.07
    Yii
    0.06
     امروز
    0.06
    -п
    0.06
      ↵↵
    0.06
     ());↵↵
    0.06
    나요
    0.06
     plung
    0.06
     isp
    0.06
    Act Density 0.048%

    No Known Activations