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

    Neuronpedia

    INDEX
    Explanations

    principle or guideline adherence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الأكثر
    0.49
    ंग्रेस
    0.46
     Zucker
    0.45
    bner
    0.44
    ότητας
    0.44
    로그
    0.44
     сроки
    0.42
    支払
    0.41
    ffe
    0.41
    ników
    0.40
    POSITIVE LOGITS
     DataSet
    0.49
    ুক
    0.44
     grazie
    0.44
     এসেছিল
    0.44
     หน่อย
    0.42
     unité
    0.42
     Sele
    0.42
     இது
    0.41
     essa
    0.41
     mals
    0.41
    Act Density 0.006%

    No Known Activations