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

    Neuronpedia

    INDEX
    Explanations

    place names and facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     si
    0.56
     s
    0.56
     pos
    0.55
     lo
    0.54
    neutral
    0.53
     =
    0.53
     sheer
    0.52
    stir
    0.52
     neutral
    0.52
     quen
    0.52
    POSITIVE LOGITS
     한국
    1.09
    韩国
    1.04
     Wisconsin
    0.98
     हरियाणा
    0.98
     Österreich
    0.97
    韓國
    0.97
     Oklahoma
    0.96
    糖尿病
    0.94
     भारत
    0.93
    台灣
    0.93
    Act Density 1.809%

    No Known Activations