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

    Neuronpedia

    INDEX
    Explanations

    financial terms and savings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    वर्तन
    0.46
    Noir
    0.42
     انصاف
    0.41
    த்ய
    0.41
    ভেল
    0.40
    Hend
    0.40
     度
    0.40
     venire
    0.39
     misunderstood
    0.39
    Aslamualaikum
    0.39
    POSITIVE LOGITS
     This
    0.46
    This
    0.45
    Savings
    0.43
     savings
    0.42
     مالی
    0.41
     Savings
    0.41
     $>$
    0.41
    $>$
    0.40
     fiduciary
    0.39
     Estas
    0.39
    Act Density 0.000%

    No Known Activations