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

    Neuronpedia

    INDEX
    Explanations

    you with a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stickers
    0.47
     Intu
    0.45
    饰演
    0.44
    谀
    0.44
    бы
    0.43
    wifi
    0.43
     sticker
    0.42
     общения
    0.42
     Embroidery
    0.42
     geändert
    0.42
    POSITIVE LOGITS
    다
    0.55
     چ
    0.52
     ನಿರ್
    0.52
     الع
    0.50
     ધ
    0.49
     学習
    0.49
     ಆ
    0.48
     ç
    0.48
     ކ
    0.48
     maggior
    0.48
    Act Density 0.000%

    No Known Activations