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

    Neuronpedia

    INDEX
    Explanations

    New Zealand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    York
    1.46
     YORK
    1.36
     York
    1.34
    york
    1.23
     york
    1.19
    यॉर्क
    1.13
     Yok
    1.11
    Yok
    1.05
    yor
    0.97
     YOK
    0.94
    POSITIVE LOGITS
     Ze
    0.80
    Ze
    0.78
     Zealand
    0.77
     southwest
    0.75
    ដ្ឋ
    0.73
     Zel
    0.71
    isional
    0.71
    जीलैंड
    0.71
    ziehungs
    0.70
     ZE
    0.68
    Act Density 0.011%

    No Known Activations