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

    Neuronpedia

    INDEX
    Explanations

    variations of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.34
     asunto
    0.33
     destinés
    0.32
     znajdują
    0.32
     zostały
    0.31
     binnen
    0.31
     Crystal
    0.31
     Fourier
    0.31
     urząd
    0.31
     különböző
    0.31
    POSITIVE LOGITS
     кстати
    0.42
     కూడా
    0.42
     даже
    0.38
     туда
    0.38
    上也
    0.38
     भी
    0.38
    因为它
    0.38
     גם
    0.38
    টিও
    0.37
     inoltre
    0.37
    Act Density 0.237%

    No Known Activations