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

    Neuronpedia

    INDEX
    Explanations

    variety of contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     защиту
    0.48
     beim
    0.46
     ശക്ത
    0.46
     sonrası
    0.45
     помощь
    0.44
     барои
    0.44
     감사합니다
    0.43
     finais
    0.43
     фина
    0.43
     proteção
    0.42
    POSITIVE LOGITS
     nejen
    0.48
     sogen
    0.46
     everything
    0.45
     tất
    0.45
     cosidd
    0.45
    :
    0.43
     myriad
    0.43
    不仅
    0.43
     sogenannte
    0.42
     настолько
    0.40
    Act Density 0.080%

    No Known Activations