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

    Neuronpedia

    INDEX
    Explanations

    data and trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     지급
    0.41
    Codes
    0.39
    ence
    0.38
     bids
    0.35
     donate
    0.35
     potentially
    0.34
    precise
    0.34
    Code
    0.34
    beitung
    0.34
    윅
    0.33
    POSITIVE LOGITS
     porówn
    0.42
    이지만
    0.41
     awalnya
    0.40
     obiettivo
    0.40
     prazer
    0.38
     немного
    0.38
    جد
    0.37
     treinta
    0.37
     biliary
    0.37
     همد
    0.37
    Act Density 0.005%

    No Known Activations