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

    Neuronpedia

    INDEX
    Explanations

    attackers and intruders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    悩み
    0.88
     unpublished
    0.83
     osią
    0.81
     ビタミン
    0.79
     nuanced
    0.78
     accomplishments
    0.75
     achievements
    0.75
    韜
    0.75
    erequisites
    0.75
    口碑
    0.74
    POSITIVE LOGITS
     intruders
    1.86
     agents
    1.69
     attackers
    1.63
     visitors
    1.55
     invaders
    1.54
     Agents
    1.44
     agentes
    1.44
     vehicles
    1.42
     troops
    1.42
     helicopters
    1.41
    Act Density 0.632%

    No Known Activations