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

    Neuronpedia

    INDEX
    Explanations

    Soviet, Chinese, and Brazilian terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    говари
    0.42
    Ско
    0.41
     बेल
    0.39
    arre
    0.38
    EAR
    0.37
    郄
    0.37
     Franken
    0.36
    صالات
    0.36
     коммуника
    0.36
     Skop
    0.36
    POSITIVE LOGITS
    badges
    0.38
    nft
    0.38
    Directory
    0.37
     Рус
    0.37
    尤其是
    0.37
    巴西
    0.36
    PhotoMode
    0.35
    尤其
    0.35
     quietly
    0.35
    ামো
    0.34
    Act Density 0.001%

    No Known Activations