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

    Neuronpedia

    INDEX
    Explanations

    pay-as-you-go

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ata
    0.40
    uri
    0.39
    em
    0.39
    alta
    0.39
     is
    0.38
    i
    0.38
     Macmillan
    0.37
     Macintosh
    0.37
     rotated
    0.37
     normalized
    0.37
    POSITIVE LOGITS
    مجھے
    0.50
     ءَ
    0.48
    -])
    0.48
    쑹
    0.47
     Сьогодні
    0.47
     вважа
    0.47
    旣
    0.47
    Notwithstanding
    0.46
    Flagge
    0.46
    ?..
    0.46
    Act Density 0.005%

    No Known Activations