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

    Neuronpedia

    INDEX
    Explanations

    increase or decrease

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    組み立て
    0.63
     steckt
    0.63
     მიმოწერა
    0.59
     яких
    0.59
    翛
    0.59
     ہماری
    0.58
     மனை
    0.56
    getNome
    0.56
    曛
    0.56
     제목
    0.55
    POSITIVE LOGITS
     liczba
    0.58
     yüzde
    0.57
     vuonna
    0.57
    0.57
     unprecedented
    0.56
     warga
    0.55
    在了
    0.55
     dramatically
    0.54
    ในปี
    0.53
    ្នុង
    0.52
    Act Density 0.002%

    No Known Activations