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

    Neuronpedia

    INDEX
    Explanations

    alternative options, representation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     from
    0.37
    پ
    0.36
     Zugang
    0.35
     teh
    0.35
     with
    0.35
    يرا
    0.34
    ي
    0.34
     reproduction
    0.34
     depl
    0.33
     Cabinet
    0.33
    POSITIVE LOGITS
     больше
    0.42
     oftentimes
    0.40
    ৃতি
    0.40
    ௦
    0.39
     एवरेज
    0.38
    זי
    0.38
    มากกว่า
    0.38
    晧
    0.38
     подобные
    0.38
    üğünüz
    0.37
    Act Density 0.031%

    No Known Activations