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

    Neuronpedia

    INDEX
    Explanations

    natural numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.54
     bijz
    0.47
    Singleton
    0.44
    ja
    0.44
     главы
    0.43
    Transactions
    0.43
     đậu
    0.42
    та
    0.41
    ？）
    0.41
    <0x92>
    0.40
    POSITIVE LOGITS
    기는
    0.49
     அனைவருக்கும்
    0.46
     istnieje
    0.45
     स्कीम
    0.45
     सिलेबस
    0.44
    iéndose
    0.44
    되면
    0.44
     배열
    0.44
    detailed
    0.43
    sulfonyl
    0.43
    Act Density 0.011%

    No Known Activations