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

    Neuronpedia

    INDEX
    Explanations

    numbers 30, 32, 33, 35, 38

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tew
    0.51
     NT
    0.41
     १५
    0.36
    0.36
    ⑮
    0.36
    ৫৫
    0.35
     درد
    0.34
     quartic
    0.34
     ५
    0.34
    ழுக
    0.34
    POSITIVE LOGITS
    8
    0.53
    9
    0.52
     thirty
    0.51
    <0xBF>
    0.50
     eighty
    0.49
    ২৯
    0.49
     ৩০
    0.47
     acht
    0.46
     तीस
    0.46
     восем
    0.46
    Act Density 0.008%

    No Known Activations