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

    Neuronpedia

    INDEX
    Explanations

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ৫
    0.20
     Nếu
    0.19
    ،
    0.19
     valamint
    0.19
     huyện
    0.18
     partitioned
    0.18
    创建一个
    0.18
     galley
    0.17
    ，
    0.17
     medallions
    0.17
    POSITIVE LOGITS
     it
    0.24
    其
    0.24
     its
    0.22
     względu
    0.21
    interesse
    0.21
     მათი
    0.21
     он
    0.21
    はその
    0.21
     their
    0.20
     їх
    0.20
    Act Density 0.399%

    No Known Activations