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

    Neuronpedia

    INDEX
    Explanations

    religion and demographics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocortic
    0.34
    Recall
    0.33
     بلکہ
    0.32
    પ્ત
    0.32
    圻
    0.32
     पढ़ने
    0.31
     כדי
    0.31
     lä
    0.30
    褒
    0.30
    idegg
    0.30
    POSITIVE LOGITS
     পরিবেশে
    0.35
     analytic
    0.32
     html
    0.31
     triunfo
    0.31
     strength
    0.31
     Brian
    0.31
     Michelle
    0.30
    めでとう
    0.30
     Environment
    0.30
     જિલ્
    0.30
    Act Density 0.003%

    No Known Activations