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

    Neuronpedia

    INDEX
    Explanations

    dungeons and dragons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Algorithm
    0.83
    oxidation
    0.78
    ֱ
    0.75
    泫
    0.74
    algorithm
    0.72
     oxidation
    0.71
     ஆராய்ச்சிய
    0.69
     नाइट्रोजन
    0.69
    والي
    0.68
    踮
    0.67
    POSITIVE LOGITS
     dice
    1.64
     campaign
    1.50
    Dice
    1.49
     Role
    1.47
     role
    1.42
    Role
    1.40
    Campaign
    1.39
    dice
    1.38
     tabletop
    1.38
     Dungeon
    1.36
    Act Density 0.451%

    No Known Activations