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

    Neuronpedia

    INDEX
    Explanations

    IKEA instructions/products

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     معت
    -0.09
     празд
    -0.09
     несмотря
    -0.09
     معتبر
    -0.08
     resto
    -0.08
     мужчина
    -0.08
    百分
    -0.08
     окаж
    -0.08
     потер
    -0.08
     кож
    -0.08
    POSITIVE LOGITS
     Sonata
    0.08
     glyph
    0.07
     APIs
    0.07
     giao
    0.07
     테스트
    0.07
     framework
    0.07
    /test
    0.07
     inference
    0.07
    Rose
    0.07
     API
    0.07
    Act Density 0.031%

    No Known Activations