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

    Neuronpedia

    INDEX
    Explanations

    wants and preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    これも
    0.35
     वहीं
    0.32
    ლებიც
    0.31
     რე
    0.30
    这也
    0.29
     ইহাতে
    0.28
    ίνει
    0.28
    GoObject
    0.28
     yaptık
    0.28
     behaves
    0.28
    POSITIVE LOGITS
     muốn
    1.23
     want
    1.23
     ingin
    1.16
     wanting
    1.14
    want
    1.09
    ต้องการ
    1.09
     wanted
    1.08
     Want
    1.03
    Want
    1.03
    想要
    1.02
    Act Density 0.536%

    No Known Activations