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

    Neuronpedia

    INDEX
    Explanations

    questions about color

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     umfass
    0.37
     umfang
    0.34
     obsah
    0.34
    clusively
    0.30
    partisan
    0.30
    ‬
    0.29
     ၁
    0.29
     atuação
    0.29
     परिणाम
    0.29
    sequ
    0.28
    POSITIVE LOGITS
    羮
    0.32
    ology
    0.32
    为什么
    0.32
    ellants
    0.31
     Pourquoi
    0.31
    瑢
    0.30
    禟
    0.30
     যুক্তরাজ্যের
    0.29
     kangaroo
    0.29
    égard
    0.29
    Act Density 0.027%

    No Known Activations