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

    Neuronpedia

    INDEX
    Explanations

    miles/kilometers and distances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Somewhere
    0.43
     kaçtır
    0.42
     situé
    0.41
     Angebot
    0.39
     Bildung
    0.39
     fortuit
    0.38
     څنګه
    0.38
     ভাগে
    0.38
     snatched
    0.37
     halfway
    0.37
    POSITIVE LOGITS
     distances
    0.60
     straight
    0.51
     STRAIGHT
    0.50
    straight
    0.50
     uninterrupted
    0.50
    Straight
    0.50
    distances
    0.50
     расстояние
    0.48
     distance
    0.47
    Distance
    0.46
    Act Density 0.012%

    No Known Activations