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

    Neuronpedia

    INDEX
    Explanations

    spoken Dravidian languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     konfl
    0.46
    磪
    0.44
     керу
    0.42
     восстанов
    0.42
     trá
    0.41
    ല്ലോ
    0.41
    ന്നാ
    0.41
     nyní
    0.41
     mö
    0.40
    🏄
    0.40
    POSITIVE LOGITS
    頎
    0.45
     hires
    0.45
     vaccines
    0.45
     copies
    0.44
    Ε
    0.44
    뻥
    0.44
     illiterate
    0.42
     bartenders
    0.42
     courier
    0.42
     clerks
    0.42
    Act Density 0.012%

    No Known Activations