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

    Neuronpedia

    INDEX
    Explanations

    programming and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ன்
    1.23
    ص
    1.08
    strasse
    1.06
    ,
    1.02
     was
    0.98
    ships
    0.98
    ن
    0.98
    ية
    0.98
     and
    0.96
    sson
    0.96
    POSITIVE LOGITS
    ।
    1.25
     начало
    1.15
    yı
    1.06
     dụng
    0.98
    。
    0.98
    ྒ
    0.98
     밝혔
    0.96
     постро
    0.95
     Ağustos
    0.95
     използва
    0.93
    Act Density 0.233%

    No Known Activations