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

    Neuronpedia

    INDEX
    Explanations

    Finnish places and common suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    énées
    0.74
     செயல
    0.74
    antro
    0.72
     ನಡೆದ
    0.72
    కుల
    0.72
    schod
    0.71
     በፍ
    0.71
    ৈর
    0.70
    ப்படுக
    0.70
    comend
    0.69
    POSITIVE LOGITS
    ainen
    0.72
    განი
    0.67
    先后
    0.66
     আসামি
    0.65
    いは
    0.65
    스는
    0.64
    konen
    0.63
     simultaneously
    0.62
    یں
    0.61
    ორი
    0.61
    Act Density 0.006%

    No Known Activations