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

    Neuronpedia

    INDEX
    Explanations

    Greek names and surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bodrum
    0.45
     pertes
    0.43
     Croatia
    0.42
     ম্যা
    0.42
     insist
    0.40
     erinnert
    0.39
     OSCE
    0.39
    資本
    0.39
    𒁕
    0.38
     archivo
    0.38
    POSITIVE LOGITS
     gentleman
    0.39
    डू
    0.38
    గి
    0.38
    хан
    0.38
    キャンペーン
    0.37
    λης
    0.37
     গিয়
    0.37
    гать
    0.37
    صاب
    0.37
    ぢ
    0.37
    Act Density 0.005%

    No Known Activations