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

    Neuronpedia

    INDEX
    Explanations

    presidential figures and government offices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     visionary
    0.61
     hegemony
    0.51
     manifesto
    0.46
     parlament
    0.43
     defensor
    0.43
     discurso
    0.43
     charisma
    0.43
     communist
    0.43
     authoritarian
    0.43
     feminists
    0.43
    POSITIVE LOGITS
     Presidential
    0.59
    protocol
    0.46
     protocols
    0.45
    总统
    0.45
     presidential
    0.45
     Palace
    0.45
     protocol
    0.45
    宫
    0.45
     Wallace
    0.44
     Fitness
    0.43
    Act Density 0.103%

    No Known Activations