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

    Neuronpedia

    INDEX
    Explanations

    medical care or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginning
    0.44
    ت
    0.44
     Guadeloupe
    0.44
     Books
    0.43
     making
    0.40
     hearing
    0.40
     Greece
    0.39
     unifying
    0.39
     Gottfried
    0.39
    able
    0.39
    POSITIVE LOGITS
    ழ்ப
    0.46
     লাগানো
    0.46
    нологи
    0.42
    ણમાં
    0.42
    涡
    0.42
    idaknya
    0.40
    ແ
    0.39
     думать
    0.38
     CONTROL
    0.38
    आव
    0.38
    Act Density 0.041%

    No Known Activations