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

    Neuronpedia

    INDEX
    Explanations

    about to happen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tendremos
    0.44
     imprescind
    0.42
     predicting
    0.41
    予想
    0.41
     inevitable
    0.41
     erwart
    0.39
     worrying
    0.39
     feared
    0.38
    SaveChanges
    0.38
     mys
    0.38
    POSITIVE LOGITS
     verge
    0.67
    即将
    0.65
     Verge
    0.61
     hendak
    0.59
    กำลัง
    0.53
    going
    0.53
    బో
    0.50
    正在
    0.49
    process
    0.47
     gonna
    0.47
    Act Density 0.015%

    No Known Activations