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

    Neuronpedia

    INDEX
    Explanations

    prevented rebellion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     البلد
    0.47
     المعلومات
    0.47
     notizie
    0.44
     seleção
    0.44
    </h3>
    0.43
    خبار
    0.41
    仍
    0.41
     складі
    0.40
     మ
    0.40
    celi
    0.40
    POSITIVE LOGITS
     nourishment
    0.47
     inorganic
    0.45
     exfoli
    0.45
    oft
    0.43
     Execution
    0.43
     Seasons
    0.42
     behavioural
    0.42
     finer
    0.42
    ாளர்களுக்கு
    0.41
    いくつ
    0.41
    Act Density 0.004%

    No Known Activations