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

    Neuronpedia

    INDEX
    Explanations

    lists of concepts and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cektir
    0.31
    したがって
    0.30
     ತೆಗೆದುಕೊಳ್ಳ
    0.29
    \%.
    0.29
     sogenannten
    0.29
     أحد
    0.28
     jeweil
    0.28
     correspondingly
    0.28
    \".
    0.28
    됩니다
    0.28
    POSITIVE LOGITS
    、
    0.83
     、
    0.64
    ၊
    0.64
    ፣
    0.63
     ,
    0.55
    ﹑
    0.53
    ،
    0.52
    ､
    0.52
    、“
    0.52
     、,
    0.51
    Act Density 0.369%

    No Known Activations