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

    Neuronpedia

    INDEX
    Explanations

    liking and enjoyment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Notify
    0.37
     numbness
    0.36
     illustrious
    0.35
     experiential
    0.35
    →</
    0.34
    ésére
    0.34
     আশ্চর্য
    0.34
    묻
    0.34
     num
    0.34
    могою
    0.33
    POSITIVE LOGITS
    喜欢
    2.86
    喜歡
    2.72
     liking
    2.69
     liked
    2.67
    ชอบ
    2.53
     likes
    2.45
     ชอบ
    2.34
    liked
    2.20
     좋아
    2.20
     gosta
    2.14
    Act Density 0.133%

    No Known Activations