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

    Neuronpedia

    INDEX
    Explanations

    knowing and understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⣤
    0.37
    聋
    0.36
     subst
    0.35
    🛴
    0.35
    呸
    0.35
    ர்ச்சி
    0.35
     Fam
    0.35
     ప్రముఖ
    0.35
     difficulties
    0.34
     разобра
    0.34
    POSITIVE LOGITS
     knowing
    2.72
    knowing
    2.41
     Knowing
    2.34
    知道
    2.33
    Knowing
    2.30
     know
    2.03
     biết
    1.98
     knows
    1.97
     knew
    1.93
     KNOW
    1.91
    Act Density 0.019%

    No Known Activations