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

    Neuronpedia

    INDEX
    Explanations

    all, alle, toutes, tutte

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ওনা
    0.46
     оказался
    0.43
     относится
    0.42
    询问
    0.42
    蛎
    0.42
    ivating
    0.41
    otica
    0.41
    蒎
    0.40
     отра
    0.40
     которому
    0.40
    POSITIVE LOGITS
    Num
    0.49
     wszystkie
    0.47
     tutte
    0.46
     toutes
    0.44
     diesen
    0.44
     Toutes
    0.43
     Num
    0.42
     ہاں
    0.42
     saepe
    0.42
     všechny
    0.41
    Act Density 0.016%

    No Known Activations