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

    Neuronpedia

    INDEX
    Explanations

    code and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maupun
    1.66
     serta
    1.43
     તેમજ
    1.33
     ايضا
    1.30
     sowie
    1.23
     tambien
    1.18
     aswell
    1.16
     lẫn
    1.13
     auch
    1.13
     myös
    1.12
    POSITIVE LOGITS
    并
    1.90
     并
    1.81
     แล้ว
    1.50
    並
    1.48
     then
    1.43
    然后
    1.35
     rồi
    1.35
     Then
    1.34
     並
    1.33
    并将
    1.30
    Act Density 0.225%

    No Known Activations