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

    Neuronpedia

    INDEX
    Explanations

    Hazard identification and risk assessment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    すすめ
    0.52
    ३
    0.49
    에
    0.49
    서
    0.48
     של
    0.47
     UN
    0.46
    요
    0.46
     &
    0.45
    تی
    0.45
     기능을
    0.44
    POSITIVE LOGITS
    jaar
    0.58
    Assemblée
    0.57
    يت
    0.52
     bör
    0.52
    ينا
    0.52
    zetten
    0.50
     elke
    0.49
     desean
    0.49
    FileUtils
    0.49
    碼
    0.48
    Act Density 0.000%

    No Known Activations