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

    Neuronpedia

    INDEX
    Explanations

    diplomatic meetings and diplomacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    从此
    0.52
     الجذر
    0.51
     ڈیٹا
    0.49
    玛
    0.48
    Ethyl
    0.48
    Trich
    0.48
     Ethyl
    0.47
    法则
    0.47
     Jenn
    0.47
     Bootstrap
    0.46
    POSITIVE LOGITS
     diplomatic
    1.14
    meetings
    1.14
     meetings
    1.12
     diplomacy
    1.12
     diplomats
    1.05
     diplom
    1.02
     bilateral
    0.98
     дипло
    0.97
     bilater
    0.96
    dipl
    0.95
    Act Density 0.011%

    No Known Activations