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
     المهنة
    -0.07
    書館
    -0.06
    隆
    -0.06
    伦
    -0.06
     tastes
    -0.06
    ③
    -0.06
     Laud
    -0.06
     Beled
    -0.06
    .kr
    -0.06
     lunar
    -0.06
    POSITIVE LOGITS
     siêu
    0.07
     ));↵↵
    0.07
    pal
    0.07
    ###↵↵
    0.07
     stemming
    0.07
     pelos
    0.07
     rects
    0.06
     disadvantaged
    0.06
     kullanımı
    0.06
    genres
    0.06
    Act Density 0.143%

    No Known Activations