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

    Neuronpedia

    INDEX
    Explanations

    film synopsis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aussi
    0.46
    ინგ
    0.45
     Cadastro
    0.43
     अलावा
    0.41
    And
    0.41
    Klas
    0.40
    データ
    0.40
     Klas
    0.40
    Não
    0.39
     fares
    0.39
    POSITIVE LOGITS
     அதி
    0.46
     设计
    0.46
     имели
    0.46
     защи
    0.45
     আশ্রয়
    0.45
    רות
    0.45
     chính
    0.45
     опреде
    0.45
     እንኳ
    0.44
     решили
    0.44
    Act Density 0.006%

    No Known Activations