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

    Neuronpedia

    INDEX
    Explanations

    age, fan, copywriting, nourishment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     attract
    0.44
     attractiveness
    0.41
    र्फ
    0.39
    मन
    0.39
    ceedings
    0.39
    ならない
    0.39
     approving
    0.38
    acyjnych
    0.38
     screenSize
    0.38
     Listings
    0.38
    POSITIVE LOGITS
    ῾
    0.51
     своего
    0.49
     իր
    0.48
     Tahiti
    0.47
     '+':
    0.47
    ૮
    0.46
     люд
    0.45
    gé
    0.44
     οι
    0.44
    số
    0.44
    Act Density 0.006%

    No Known Activations