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

    Neuronpedia

    INDEX
    Explanations

    de la

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    1.55
     fiercely
    1.31
    ро
    1.27
    ो
    1.25
    не
    1.23
     phương
    1.22
    на
    1.20
     vicinity
    1.20
     거
    1.19
    ことで
    1.19
    POSITIVE LOGITS
    すすめ
    1.46
    '
    1.44
     жив
    1.38
    Slf
    1.35
     partire
    1.30
     ومن
    1.27
    .])
    1.19
    TimeStamp
    1.19
     questione
    1.18
    ']}
    1.16
    Act Density 0.060%

    No Known Activations