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

    Neuronpedia

    INDEX
    Explanations

    countries and territories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пси
    0.38
     uninterrupted
    0.38
     मंगल
    0.38
    vili
    0.37
     doen
    0.37
     unsh
    0.37
     matrícula
    0.36
     опу
    0.36
     பய
    0.36
    フグ
    0.36
    POSITIVE LOGITS
     diplomats
    0.45
    Worldwide
    0.45
     worldwide
    0.43
    worldwide
    0.43
    各国
    0.42
     Offices
    0.41
    Israeli
    0.40
     Ambassador
    0.39
     States
    0.39
    mer
    0.38
    Act Density 0.001%

    No Known Activations