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

    Neuronpedia

    INDEX
    Explanations

    nationalities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    度和
    0.57
    মাত্রা
    0.54
    度的
    0.53
     fame
    0.49
    дови
    0.49
    ме
    0.48
     dome
    0.48
     rental
    0.47
    λέ
    0.47
    жо
    0.46
    POSITIVE LOGITS
    Asian
    0.93
    InCM
    0.85
    Indonesia
    0.80
    Ukrainian
    0.78
     Ungarn
    0.78
    Czechoslovakia
    0.76
     Indonesian
    0.76
    OLD
    0.76
     Namib
    0.75
    Brazilian
    0.75
    Act Density 0.000%

    No Known Activations