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

    Neuronpedia

    INDEX
    Explanations

    recent and upcoming events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualité
    0.41
     surtout
    0.40
     vraiment
    0.38
    ವುದು
    0.38
     onError
    0.38
     dość
    0.38
    どもの
    0.37
     adipisicing
    0.37
     assez
    0.36
     geste
    0.36
    POSITIVE LOGITS
     upcoming
    1.80
    即将
    1.63
    upcoming
    1.59
     recently
    1.53
     forthcoming
    1.50
     Upcoming
    1.49
    Upcoming
    1.49
     предстоя
    1.42
     недавно
    1.39
    正在
    1.37
    Act Density 0.010%

    No Known Activations