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

    Neuronpedia

    INDEX
    Explanations

    abstract nouns and gerunds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.02
    te
    0.97
    o
    0.92
    l
    0.87
    a
    0.85
    ০
    0.83
    it
    0.83
    ו
    0.80
    जिन
    0.76
     medida
    0.76
    POSITIVE LOGITS
     हाईकोर्ट
    1.10
     الق
    1.05
    𝒚
    1.01
     ي
    1.01
     ه
    0.98
     ت
    0.97
    ﹕
    0.97
     Realm
    0.96
     إ
    0.93
    <0xF3>
    0.93
    Act Density 0.418%

    No Known Activations