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

    Neuronpedia

    INDEX
    Explanations

    people who care

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    喜爱
    0.39
     loving
    0.39
     люби
    0.38
    ânia
    0.38
     tipped
    0.38
     réduite
    0.38
     liking
    0.38
    ശാല
    0.38
    omatic
    0.37
    ชอบ
    0.37
    POSITIVE LOGITS
     know
    0.42
    喆
    0.39
     знаю
    0.39
     biết
    0.36
     الأد
    0.36
    ゲル
    0.36
     medica
    0.36
    )-$
    0.35
     Schwartz
    0.34
    作文
    0.34
    Act Density 0.002%

    No Known Activations