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

    Neuronpedia

    INDEX
    Explanations

    space mission components and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flücht
    0.80
     invade
    0.75
     বেতার
    0.72
    prisoners
    0.72
     invading
    0.71
     profesión
    0.70
    紊
    0.69
    NSInteger
    0.69
    ISTANCE
    0.68
     invaders
    0.68
    POSITIVE LOGITS
     mission
    1.18
     subarrays
    1.12
     Mission
    1.10
     subarray
    1.09
     onboard
    1.08
    Mission
    1.04
     deploy
    1.04
     Payload
    0.99
    subarray
    0.98
    mission
    0.96
    Act Density 0.171%

    No Known Activations