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

    Neuronpedia

    INDEX
    Explanations

    defining what it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.32
     (
    0.31
     x
    0.31
     with
    0.31
    4
    0.30
    2
    0.29
     +
    0.29
     \
    0.28
    ',
    0.27
    ,
    0.27
    POSITIVE LOGITS
    <unused1158>
    0.25
     человек
    0.25
     situações
    0.24
    ције
    0.24
    Despatx
    0.24
    <unused406>
    0.23
    тья
    0.23
    <unused581>
    0.23
    κτήθηκε
    0.23
    Вакансия
    0.23
    Act Density 2.842%

    No Known Activations