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

    Neuronpedia

    INDEX
    Explanations

    this is arguably the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    分辨
    0.71
     पूरी
    0.70
     احت
    0.68
     основном
    0.67
     basados
    0.66
    坚持
    0.64
     estaven
    0.63
     সম্পূর্ন
    0.63
     সম্পূর্ণ
    0.63
    ্যায়
    0.63
    POSITIVE LOGITS
     prime
    0.87
     Prime
    0.85
     PRIME
    0.83
    Prime
    0.77
    prime
    0.77
     primo
    0.75
    Priority
    0.75
     desperation
    0.71
     thematic
    0.71
    キーワード
    0.70
    Act Density 0.523%

    No Known Activations