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

    Neuronpedia

    INDEX
    Explanations

    Generative AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    2.02
    る
    1.90
    り
    1.88
    ता
    1.84
    ৮
    1.73
    ৪
    1.66
    ্লাহ
    1.64
    お子
    1.64
    穵
    1.63
    ोर
    1.61
    POSITIVE LOGITS
     sebab
    1.24
    peptide
    1.23
    -
    1.19
    ↵
    1.11
     към
    1.11
    ци
    1.10
     justru
    1.09
     Skyscrapers
    1.09
     चूंकि
    1.08
     totalPrice
    1.08
    Act Density 0.040%

    No Known Activations