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

    Neuronpedia

    INDEX
    Explanations

    Australian locations and place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     difund
    0.42
    yd
    0.41
     immortal
    0.39
    ypi
    0.38
    ウル
    0.38
    ոտ
    0.38
    氫
    0.38
    విద్య
    0.37
    making
    0.37
    ตัน
    0.37
    POSITIVE LOGITS
     Ku
    0.73
     ku
    0.67
    Ku
    0.67
     Newport
    0.55
     Pitt
    0.54
     Palm
    0.52
     Collar
    0.52
     Avalon
    0.51
    Palm
    0.50
     Narr
    0.49
    Act Density 0.002%

    No Known Activations