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

    Neuronpedia

    INDEX
    Explanations

    such , regard ,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    0.57
    izioni
    0.54
     cardí
    0.54
     Floral
    0.52
     encontr
    0.51
    िंग
    0.50
    ête
    0.49
    ))$
    0.49
     Fleurs
    0.49
    ens
    0.48
    POSITIVE LOGITS
     an
    0.69
    c
    0.65
    a
    0.65
     ພວກເຮົາ
    0.56
     ആരംഭ
    0.55
     в
    0.52
     ຈ
    0.52
    b
    0.52
    𝗖
    0.51
     irrevoc
    0.50
    Act Density 0.055%

    No Known Activations