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

    Neuronpedia

    INDEX
    Explanations

    places and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eines
    0.71
     vergang
    0.67
     unui
    0.67
    paragraph
    0.67
     の
    0.66
     eventuali
    0.66
     unei
    0.66
     volled
    0.66
     vollständ
    0.65
     seorang
    0.64
    POSITIVE LOGITS
     Europe
    2.98
     France
    2.64
     Germany
    2.63
     Italy
    2.52
    Europe
    2.48
     Australia
    2.45
     England
    2.42
     Spain
    2.39
     Japan
    2.37
    Germany
    2.35
    Act Density 0.155%

    No Known Activations