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

    Neuronpedia

    INDEX
    Explanations

    takes time or longer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Need
    0.36
     suficientes
    0.36
     Enough
    0.35
     autonomous
    0.34
     genoeg
    0.32
    낮
    0.32
    autonomous
    0.31
    Autonomous
    0.31
     sq
    0.31
     зада
    0.31
    POSITIVE LOGITS
     longer
    0.79
     awhile
    0.79
     länger
    0.71
    longer
    0.71
     Longer
    0.60
     dłu
    0.59
     זמן
    0.58
     längre
    0.54
     forever
    0.53
     وقت
    0.53
    Act Density 0.014%

    No Known Activations