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

    Neuronpedia

    INDEX
    Explanations

    common, ruby, column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beque
    0.52
     bereaved
    0.51
    a
    0.51
     לח
    0.49
    プレ
    0.49
    ו
    0.49
    o
    0.48
     усилия
    0.48
     renew
    0.48
    rames
    0.48
    POSITIVE LOGITS
     rohkem
    0.54
     മണിക്ക
    0.52
     forskjellige
    0.51
    Eine
    0.49
     spiega
    0.49
     як
    0.48
     comunicazione
    0.48
     udah
    0.46
     cœur
    0.46
     sabah
    0.46
    Act Density 0.000%

    No Known Activations