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

    Neuronpedia

    INDEX
    Explanations

    dodging obstacles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gaming
    0.87
    Gaming
    0.82
     GM
    0.79
    🎲
    0.77
     CPM
    0.76
    Drama
    0.75
    GST
    0.74
     Poker
    0.73
     покер
    0.73
    седнев
    0.73
    POSITIVE LOGITS
     obstacle
    1.09
     obstacles
    1.05
     rescue
    0.96
     rescuing
    0.95
     dodging
    0.93
     obstructions
    0.93
     missions
    0.90
    obstacles
    0.88
     ultrasonic
    0.87
     obstruct
    0.87
    Act Density 0.279%

    No Known Activations