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

    Neuronpedia

    INDEX
    Explanations

    language identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    们的
    0.69
     deh
    0.67
    ங்களின்
    0.63
     wooden
    0.59
     griega
    0.58
     গুলোতে
    0.56
    们
    0.56
     Wooden
    0.55
     Halls
    0.54
     Filipino
    0.54
    POSITIVE LOGITS
    language
    1.26
     language
    1.22
     Language
    1.15
    Language
    1.09
     язык
    1.09
    语言
    1.09
     scripts
    1.04
     script
    1.01
     версии
    1.00
    版
    1.00
    Act Density 0.438%

    No Known Activations