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

    Neuronpedia

    INDEX
    Explanations

    aforementioned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ூட
    0.37
    ibatkan
    0.36
    ések
    0.36
     रणबीर
    0.36
    ृ
    0.35
    тропо
    0.35
    बर
    0.35
     यात
    0.35
     ગુજરા
    0.34
    र्तन
    0.34
    POSITIVE LOGITS
     mentioned
    2.84
     aforementioned
    2.50
    mentioned
    2.44
     mencionado
    2.33
     mencionados
    2.20
     mencion
    2.06
     aforesaid
    1.91
    提到的
    1.88
     مذکور
    1.86
     erwäh
    1.80
    Act Density 0.075%

    No Known Activations