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

    Neuronpedia

    INDEX
    Explanations

    dialogue starts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ならば
    0.45
     তাহা
    0.43
     zejména
    0.43
    倘
    0.42
     Пусть
    0.41
    曾经
    0.40
     apartness
    0.39
     colloc
    0.39
    洊
    0.39
     많
    0.39
    POSITIVE LOGITS
     proceed
    0.82
     proceeded
    0.82
    proceed
    0.80
     proceeds
    0.75
    Proceed
    0.70
     Proceed
    0.69
     proceeding
    0.68
     Proceeds
    0.63
     promptly
    0.61
     yells
    0.61
    Act Density 0.033%

    No Known Activations