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

    Neuronpedia

    INDEX
    Explanations

    practical information * and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Orange
    0.46
    Fluent
    0.46
    يش
    0.44
    вершен
    0.43
    лизи
    0.42
     squat
    0.42
     tê
    0.40
    মধ্যে
    0.39
    انو
    0.39
     racked
    0.39
    POSITIVE LOGITS
    ḕ
    0.53
    ពេលវេល
    0.49
    の話
    0.49
     և
    0.47
     gyors
    0.47
    そして
    0.47
     найкра
    0.47
     possibile
    0.46
     そして
    0.45
    糟糕
    0.45
    Act Density 0.003%

    No Known Activations