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

    Neuronpedia

    INDEX
    Explanations

    feminine roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ejemplo
    0.46
     viktigt
    0.45
    пример
    0.40
    profissional
    0.40
     performs
    0.40
     eksempel
    0.39
     अंग्रेजों
    0.39
    bodyParser
    0.38
     असंख्य
    0.38
    নিম্ন
    0.38
    POSITIVE LOGITS
     target
    0.40
     new
    0.38
    ھار
    0.38
    tions
    0.38
     expansión
    0.37
     potential
    0.36
     sugg
    0.36
     Enhancement
    0.36
     haunt
    0.36
     idea
    0.35
    Act Density 0.002%

    No Known Activations