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

    Neuronpedia

    INDEX
    Explanations

    numbered lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     servers
    0.41
     lipoprotein
    0.40
     oss
    0.39
     roofs
    0.39
     workflows
    0.39
     robes
    0.39
     automakers
    0.39
     erosion
    0.39
     gases
    0.39
     insect
    0.38
    POSITIVE LOGITS
    เพิ่มเติม
    0.42
     Пере
    0.39
     편집
    0.39
    第一題
    0.39
    additional
    0.38
     подробно
    0.38
     Paragraph
    0.38
    Пере
    0.37
    編集
    0.37
     Ра
    0.37
    Act Density 0.464%

    No Known Activations