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

    Neuronpedia

    INDEX
    Explanations

    phrases following specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    覃
    0.43
     dwarves
    0.38
     dwarfs
    0.37
     достав
    0.37
     инг
    0.37
     complementarity
    0.36
    깼
    0.36
    uling
    0.36
     разли
    0.35
    玼
    0.35
    POSITIVE LOGITS
     اکس
    0.45
    板块
    0.40
    න්
    0.40
    ACES
    0.38
     kaikki
    0.38
     работаю
    0.38
     مصنوع
    0.38
     مست
    0.37
     Clip
    0.37
    Clip
    0.36
    Act Density 0.001%

    No Known Activations