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

    Neuronpedia

    INDEX
    Explanations

    .subplots

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     completes
    -0.08
    摧
    -0.07
    نت
    -0.07
    损耗
    -0.07
     revised
    -0.07
    ﹰ
    -0.07
     refine
    -0.07
     preempt
    -0.07
    interpreter
    -0.07
    _COMPONENT
    -0.07
    POSITIVE LOGITS
     отзывы
    0.08
    atron
    0.08
    יצה
    0.06
    \Seeder
    0.06
    虾
    0.06
    tığı
    0.06
    �
    0.06
    fra
    0.06
     çeşitli
    0.06
    𬭊
    0.06
    Act Density 0.001%

    No Known Activations