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

    Neuronpedia

    INDEX
    Explanations

    magnesium, minerals, and nutrients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ే
    2.29
    puzzle
    2.06
    ின்
    2.04
    р
    1.94
    ছনে
    1.92
    ాలు
    1.90
    انا
    1.90
    est
    1.85
    видно
    1.85
    त
    1.85
    POSITIVE LOGITS
    ی
    3.11
    t
    2.76
    tics
    2.76
    tic
    2.57
    י
    2.54
    கிறது
    2.53
    ು
    2.47
    s
    2.40
    sü
    2.35
    tional
    2.31
    Act Density 0.003%

    No Known Activations