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

    Neuronpedia

    INDEX
    Explanations

    actions followed by now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apology
    0.41
     باتوں
    0.41
     అర్థ
    0.41
    きちんと
    0.40
     제가
    0.40
     polite
    0.40
     coax
    0.39
     distributive
    0.39
     pleading
    0.39
    どのような
    0.38
    POSITIVE LOGITS
     today
    0.91
     now
    0.79
     сегодня
    0.79
     TODAY
    0.79
     आज
    0.78
     sekarang
    0.75
     dès
    0.72
     Today
    0.72
     NOW
    0.70
    Today
    0.70
    Act Density 0.008%

    No Known Activations