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

    Neuronpedia

    INDEX
    Explanations

    awards and legislation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     year
    0.82
     năm
    0.74
     vuonna
    0.70
     yearly
    0.68
     anului
    0.64
     año
    0.63
     বছর
    0.63
     בשנת
    0.63
     année
    0.62
    year
    0.62
    POSITIVE LOGITS
    暨
    0.50
    ucksack
    0.40
    thapi
    0.39
     módulo
    0.38
     posibles
    0.38
    日前
    0.38
    ógicas
    0.38
    벤트
    0.38
     ieri
    0.38
     sabato
    0.38
    Act Density 0.007%

    No Known Activations