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

    Neuronpedia

    INDEX
    Explanations

    create a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是谁
    1.25
    㐄
    1.23
    การ
    1.20
    ません
    1.17
    मर्रा
    1.16
    ます
    1.12
    考え
    1.12
    нды
    1.11
    世界杯
    1.11
    에서
    1.09
    POSITIVE LOGITS
     havoc
    1.80
     будто
    1.48
    ière
    1.25
    σιν
    1.19
    สรร
    1.16
     впечатление
    1.16
     ώστε
    1.16
    icción
    1.13
    rlige
    1.13
    ILING
    1.13
    Act Density 0.357%

    No Known Activations