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

    Neuronpedia

    INDEX
    Explanations

    app titles in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DWORD
    0.44
    出了
    0.42
    Ꮽ
    0.41
     அமைப்பு
    0.40
     домашних
    0.40
     মাহমুদ
    0.40
     mouvements
    0.40
    ഓം
    0.39
     জব
    0.39
     цветов
    0.39
    POSITIVE LOGITS
    려
    0.39
    ingan
    0.38
     ane
    0.37
     gal
    0.37
     separate
    0.36
    overy
    0.36
    ดังกล่าว
    0.36
     aforementioned
    0.35
     heap
    0.35
     long
    0.34
    Act Density 0.000%

    No Known Activations