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

    Neuronpedia

    INDEX
    Explanations

    late 2023 and early 2024

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    വേ
    0.82
    ৱ
    0.73
    র্ড
    0.66
    9
    0.64
    8
    0.64
    Зна
    0.63
     праз
    0.63
    장
    0.62
    next
    0.62
    ântul
    0.61
    POSITIVE LOGITS
     last
    1.33
     Last
    1.14
     последних
    1.04
     ostatnich
    1.00
     recent
    0.98
    Last
    0.97
     récent
    0.97
     récemment
    0.96
     vorige
    0.95
     последнего
    0.95
    Act Density 0.193%

    No Known Activations