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

    Neuronpedia

    INDEX
    Explanations

    of descriptive nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.28
    或其他
    0.27
    把
    0.26
     the
    0.26
    ImgBoard
    0.25
    或
    0.24
     ако
    0.23
    被
    0.23
     להיות
    0.23
    你想
    0.23
    POSITIVE LOGITS
    шенные
    0.23
     market
    0.23
     şeyler
    0.22
     animales
    0.21
     quelli
    0.21
     commodities
    0.21
     opportunities
    0.20
     viable
    0.20
     plastics
    0.20
     CDs
    0.20
    Act Density 1.444%

    No Known Activations