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

    Neuronpedia

    INDEX
    Explanations

    paradoxes and social dynamics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     উৎসব
    0.45
    激发
    0.44
    噤
    0.44
    页面
    0.43
    萦
    0.43
    Sensitivity
    0.42
     ٹرسٹ
    0.41
    Joey
    0.41
    GroupID
    0.41
    识
    0.40
    POSITIVE LOGITS
    т
    0.55
     freelancer
    0.49
     constitución
    0.46
     oración
    0.46
     variantes
    0.45
    энер
    0.45
     tačiau
    0.44
     Constitución
    0.44
     reparar
    0.44
     negoci
    0.43
    Act Density 0.001%

    No Known Activations