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

    Neuronpedia

    INDEX
    Explanations

    need to be careful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    2.77
     và
    2.71
     και
    2.51
     и
    2.30
     और
    2.28
     AND
    2.24
    ,
    2.20
     և
    2.15
    and
    2.14
     וע
    2.14
    POSITIVE LOGITS
    ћ
    1.22
    Possible
    1.17
    可以将
    1.14
    ِی
    1.14
    的に
    1.14
     ذریع
    1.13
    ভাবেই
    1.13
    Вот
    1.12
    টিও
    1.12
    Alternatively
    1.10
    Act Density 0.162%

    No Known Activations