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

    Neuronpedia

    INDEX
    Explanations

    containers for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     might
    1.57
     mungkin
    1.45
     may
    1.43
     potrebbe
    1.42
    might
    1.41
     könnte
    1.41
     pourrait
    1.40
     podría
    1.40
     อาจ
    1.40
     could
    1.39
    POSITIVE LOGITS
    围绕
    0.87
     around
    0.86
     вокруг
    0.82
     four
    0.75
     surrounding
    0.75
     encircled
    0.75
     centered
    0.73
     revolves
    0.71
    ormous
    0.71
     three
    0.70
    Act Density 0.625%

    No Known Activations