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

    Neuronpedia

    INDEX
    Explanations

    liking or disliking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erzählen
    0.58
     dimulai
    0.57
    ्यालय
    0.57
     담당
    0.57
    さん
    0.55
     brave
    0.55
     ನಡೆಸ
    0.55
     bragging
    0.55
    ご紹介
    0.55
     ዋና
    0.55
    POSITIVE LOGITS
     dislike
    1.21
     liking
    1.20
    喜歡
    1.10
    喜欢
    1.09
     preferring
    1.05
     prefer
    1.04
     admires
    1.04
     पसंद
    1.03
     prefers
    1.03
     предпочита
    1.02
    Act Density 0.396%

    No Known Activations