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

    Neuronpedia

    INDEX
    Explanations

    player move or decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    कुंड
    0.43
    DATE
    0.41
    鲵
    0.41
     filaments
    0.40
     DATE
    0.40
     흡
    0.39
     प्रोडक्ट्स
    0.39
     экземпля
    0.39
    fichier
    0.39
     фили
    0.38
    POSITIVE LOGITS
     decisions
    0.68
     choices
    0.65
     decision
    0.64
     actions
    0.61
     action
    0.59
     scelte
    0.54
     player
    0.54
     choice
    0.53
     dönt
    0.52
     Decision
    0.52
    Act Density 0.164%

    No Known Activations