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

    Neuronpedia

    INDEX
    Explanations

    suggests or prioritizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mungkin
    0.50
     Están
    0.47
    都要
    0.45
    errno
    0.43
    rashed
    0.43
    BIOS
    0.41
     Dados
    0.41
     ஒன்றை
    0.40
     Bởi
    0.40
     Possibly
    0.39
    POSITIVE LOGITS
     produt
    0.43
     ფ
    0.41
          
    0.40
     aika
    0.38
    škai
    0.38
    ाम
    0.38
     carv
    0.38
     berdasarkan
    0.37
    cially
    0.37
     continuity
    0.36
    Act Density 0.029%

    No Known Activations