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

    Neuronpedia

    INDEX
    Explanations

    words related to international relations, politics, and trade

    oai_token-act-pair · gemini-2.0-flash

    abroad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    saraba
    -0.57
     du
    -0.42
    pak
    -0.40
     Obrador
    -0.39
    cycle
    -0.39
     carcasa
    -0.38
    žuje
    -0.37
    似
    -0.37
    ظ
    -0.37
    ISP
    -0.36
    POSITIVE LOGITS
     المعيارى
    0.90
     Wikimedijinoj
    0.82
     ddelweddau
    0.77
    DispatchToProps
    0.69
     الحره
    0.67
    Хьажоргаш
    0.65
    StoryboardSegue
    0.65
     myſelf
    0.64
    IVEREF
    0.64
     الخارجية
    0.62
    Act Density 3.193%

    No Known Activations