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

    Neuronpedia

    INDEX
    Explanations

    game code snippet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resultMap
    0.44
    FindAction
    0.43
    Faction
    0.41
    Isolated
    0.40
     ぞ
    0.40
    納得
    0.39
    武装
    0.39
    ័យ
    0.38
    呋
    0.38
    Sele
    0.38
    POSITIVE LOGITS
     bouncing
    0.70
     speed
    0.70
     game
    0.68
     balls
    0.67
     score
    0.64
    speed
    0.64
     bounces
    0.63
     collision
    0.61
    score
    0.60
     moving
    0.60
    Act Density 0.045%

    No Known Activations