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

    Neuronpedia

    INDEX
    Explanations

    terrorist concerns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Optical
    0.72
     Chiropractic
    0.71
    mgr
    0.69
     Optical
    0.69
    0.69
    csv
    0.69
    Faculty
    0.68
    俞
    0.68
     Workforce
    0.67
    Jupiter
    0.65
    POSITIVE LOGITS
     terrorist
    2.27
     terrorists
    2.20
     terrorism
    2.15
     terror
    2.03
     Terror
    1.97
     Terrorism
    1.96
     терро
    1.94
    Terror
    1.91
    terror
    1.79
    terrorism
    1.77
    Act Density 0.567%

    No Known Activations