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

    Neuronpedia

    INDEX
    Explanations

    list items and numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বর্ধমান
    1.16
    oter
    1.05
     ویئر
    1.04
    azon
    1.03
    дің
    1.02
    /**
    1.02
    }}>
    1.02
    आरटी
    0.98
    一系列
    0.97
    ěst
    0.94
    POSITIVE LOGITS
    reifen
    1.27
     ders
    1.27
     sf
    1.23
     spectrom
    1.20
     ecce
    1.14
     unicorn
    1.12
     sauvegarde
    1.11
     jungen
    1.10
    merksamkeit
    1.10
     teenage
    1.10
    Act Density 0.001%

    No Known Activations