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

    Neuronpedia

    INDEX
    Explanations

    let me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Let
    1.45
     let
    1.41
    Let
    1.39
     Vamos
    1.23
     लेट्स
    1.15
    Vamos
    1.15
    let
    1.06
     başlayalım
    1.01
    让我们
    0.99
     Veamos
    0.99
    POSITIVE LOGITS
    could
    0.85
     COULD
    0.85
     could
    0.83
    striatis
    0.83
     multitude
    0.82
    lle
    0.82
    nales
    0.81
     atthakath
    0.80
    lazy
    0.80
    mie
    0.78
    Act Density 0.064%

    No Known Activations