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

    Neuronpedia

    INDEX
    Explanations

    formatted input output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আপ
    0.49
     up
    0.45
    Meth
    0.44
     jemand
    0.41
    Up
    0.41
    aneous
    0.40
    adır
    0.40
    اہد
    0.39
    iguous
    0.39
    ographic
    0.38
    POSITIVE LOGITS
     bialgebras
    0.41
     Witch
    0.40
     Lives
    0.38
    组成
    0.38
     মাটি
    0.38
     Nei
    0.38
     onion
    0.38
    േഷ്
    0.37
    的生活
    0.36
    duel
    0.36
    Act Density 0.000%

    No Known Activations