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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by variables or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     البحث
    0.61
     القيام
    0.56
    indest
    0.50
     Между
    0.50
     ውሃ
    0.50
     ලබා
    0.49
    ATUM
    0.48
     канторы
    0.48
     Klicken
    0.47
     حيات
    0.47
    POSITIVE LOGITS
     and
    0.78
     as
    0.60
     the
    0.54
    1
    0.52
     \
    0.52
     và
    0.51
    \
    0.50
    0.49
    ↵
    0.49
     multiple
    0.49
    Act Density 0.168%

    No Known Activations