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

    Neuronpedia

    INDEX
    Explanations

    quotations/titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    졌다
    -0.09
     तैय
    -0.08
     Ondanks
    -0.08
    iddwa
    -0.08
    aphezulu
    -0.08
    ابد
    -0.08
     საჭ
    -0.08
     godimo
    -0.08
    -ċ
    -0.08
    еттер
    -0.08
    POSITIVE LOGITS
     inspiración
    0.09
     quoting
    0.09
     nod
    0.09
     inspiração
    0.09
    يم
    0.08
     Lyrics
    0.08
    引用
    0.08
     quoted
    0.08
    一句
    0.08
    歌词
    0.08
    Act Density 0.036%

    No Known Activations