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

    Neuronpedia

    INDEX
    Explanations

    English questions and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تهیه
    0.38
     টেব
    0.38
     الجدول
    0.37
     ولا
    0.37
    μβρίου
    0.37
     содержа
    0.35
     اسماء
    0.35
    成本
    0.35
     Accompl
    0.34
     Bürgermeister
    0.34
    POSITIVE LOGITS
    WERS
    0.43
    abad
    0.40
    opi
    0.40
    底层
    0.39
    cepter
    0.39
    vit
    0.39
    sik
    0.38
    lice
    0.38
     outcrop
    0.37
    USTER
    0.37
    Act Density 0.865%

    No Known Activations