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

    Neuronpedia

    INDEX
    Explanations

    place names and city suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ニチイ
    1.20
    지만
    1.13
     և
    1.09
    ţă
    1.05
     ditth
    1.05
    するので
    1.04
     profusely
    1.03
    する場合は
    1.02
    ਗ
    1.01
    あの
    0.99
    POSITIVE LOGITS
    m
    1.54
    tion
    1.53
    ли
    1.52
    ло
    1.34
    ians
    1.34
    messer
    1.31
    ite
    1.30
    shire
    1.28
    ت
    1.28
    ian
    1.23
    Act Density 0.093%

    No Known Activations