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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wiltshire
    -1.07
     Leinster
    -0.93
     Sligo
    -0.92
     Kilkenny
    -0.91
     Dorset
    -0.90
     Donegal
    -0.90
    扱う
    -0.89
     Geelong
    -0.88
     Otago
    -0.88
     Gloucestershire
    -0.88
    POSITIVE LOGITS
     бампер
    0.90
    鹃
    0.88
     housing
    0.87
    cuba
    0.83
     green
    0.82
     Whit
    0.82
     Homem
    0.82
     infant
    0.81
    委員
    0.81
    宴
    0.81
    Act Density 0.111%

    No Known Activations