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

    Neuronpedia

    INDEX
    Explanations

    Violent extremism and terrorism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    导弹
    0.50
     missiles
    0.44
     вій
    0.43
     missile
    0.40
     instrucción
    0.40
     précision
    0.40
     voluptates
    0.40
    簪
    0.39
    鋰
    0.39
    扳
    0.39
    POSITIVE LOGITS
     Terrorism
    0.53
    Terror
    0.51
     terrorism
    0.50
     Terror
    0.50
     terror
    0.48
    terror
    0.46
     pressure
    0.46
     counter
    0.45
     Counter
    0.43
     Tactics
    0.43
    Act Density 0.016%

    No Known Activations