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

    Neuronpedia

    INDEX
    Explanations

    what are you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legislation
    0.52
     информация
    0.50
     evidence
    0.48
     woodwork
    0.48
     stuff
    0.47
     κόσ
    0.46
     nimic
    0.45
     evidencia
    0.45
     niemand
    0.45
    기
    0.44
    POSITIVE LOGITS
     οι
    0.61
     tři
    0.58
     dwie
    0.56
    wolves
    0.55
     люди
    0.54
     dvě
    0.51
     few
    0.51
     কয়েকটি
    0.51
     तैयारियां
    0.50
     všetky
    0.50
    Act Density 0.048%

    No Known Activations