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

    Neuronpedia

    INDEX
    Explanations

    breaking down differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     urinal
    0.55
     disponibilités
    0.48
    .",[
    0.47
     partant
    0.46
    Ꮜ
    0.46
     Geheim
    0.46
     kaisi
    0.46
     পুনরা
    0.45
     Wieder
    0.45
     Beled
    0.45
    POSITIVE LOGITS
    </
    0.54
    a
    0.50
    o
    0.50
    Eff
    0.47
     Eff
    0.44
    EFF
    0.43
     একদিকে
    0.41
     punches
    0.40
    回合
    0.40
    Placed
    0.40
    Act Density 0.001%

    No Known Activations