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

    Neuronpedia

    INDEX
    Explanations

    countries

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ---+
    0.76
    lichem
    0.71
     sami
    0.70
    urkan
    0.66
    setlength
    0.65
    зар
    0.64
    kgs
    0.62
     kvadr
    0.61
    唏
    0.60
     tan
    0.59
    POSITIVE LOGITS
     Italy
    3.32
     Japan
    3.22
     Germany
    3.17
     China
    3.16
     Spain
    3.10
     France
    3.10
     Greece
    3.03
     Australia
    2.98
    Germany
    2.96
    Japan
    2.94
    Act Density 0.046%

    No Known Activations