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

    Neuronpedia

    INDEX
    Explanations

    future intent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    えています
    0.88
    ходили
    0.81
     parfois
    0.77
    udrait
    0.75
     manchmal
    0.75
    ometimes
    0.75
     fueran
    0.75
    ைகிறது
    0.73
    วัสดี
    0.73
    されています
    0.72
    POSITIVE LOGITS
     will
    6.17
    will
    5.65
     sẽ
    5.15
     akan
    4.95
    Will
    4.88
     Will
    4.84
     WILL
    4.65
     будет
    4.34
    WILL
    4.13
     będzie
    4.08
    Act Density 1.269%

    No Known Activations