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
    みて
    1.05
    畢
    1.02
    ajari
    0.95
    ála
    0.88
    нің
    0.87
    方面的
    0.86
    jší
    0.85
    みたい
    0.84
    樞
    0.83
    まった
    0.82
    POSITIVE LOGITS
     York
    2.46
     Jersey
    2.18
     york
    2.08
    York
    2.03
    york
    1.98
     NY
    1.97
    SNL
    1.94
     CNT
    1.94
     Zealand
    1.89
    Jersey
    1.89
    Act Density 0.031%

    No Known Activations