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

    Neuronpedia

    INDEX
    Explanations

    popularity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ב
    0.45
    pid
    0.43
    ร
    0.41
     दुर्लभ
    0.40
    would
    0.40
    ாளர்களுக்கு
    0.39
    ก
    0.39
     [(
    0.39
    ৮
    0.39
     बारे
    0.38
    POSITIVE LOGITS
     populer
    0.71
     popular
    0.64
     populaire
    0.63
     populares
    0.61
     популяр
    0.59
     auprès
    0.57
     populaires
    0.57
    popular
    0.56
     choice
    0.56
    Popular
    0.55
    Act Density 0.013%

    No Known Activations