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

    Neuronpedia

    INDEX
    Explanations

    terrorism and terrorist groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.41
    ри
    1.25
    ни
    1.13
    т
    1.11
    ει
    1.10
    و
    1.00
    ו
    0.98
    י
    0.92
    ي
    0.91
    ના
    0.89
    POSITIVE LOGITS
     terrorism
    1.07
    1.07
     terrorist
    1.06
     terrorists
    0.85
     Terrorism
    0.85
     জঙ্গি
    0.84
    9
    0.80
     Terror
    0.76
    terrorism
    0.75
    Terror
    0.75
    Act Density 0.001%

    No Known Activations