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

    Neuronpedia

    INDEX
    Explanations

    ranking algorithm metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.43
    這
    0.42
    在
    0.42
     this
    0.41
     in
    0.40
    ",
    0.40
     an
    0.39
     dysfunction
    0.38
    这
    0.37
    رح
    0.37
    POSITIVE LOGITS
     دریافت
    0.45
     ricev
    0.45
     Mỗi
    0.42
     Để
    0.41
     chiens
    0.41
     দর্শকদের
    0.41
     productColor
    0.41
     Чтобы
    0.41
     composés
    0.41
     כדי
    0.39
    Act Density 0.003%

    No Known Activations