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

    Neuronpedia

    INDEX
    Explanations

    person passed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     membantu
    0.52
     gestão
    0.49
     casamento
    0.49
     encryption
    0.47
     viagens
    0.46
     جوړونکي
    0.46
     auffi
    0.46
     eyebrows
    0.45
     जास्त
    0.45
     chave
    0.45
    POSITIVE LOGITS
    с
    0.43
    ๓
    0.42
    हमारे
    0.41
    겠지만
    0.39
     notre
    0.39
    द्य
    0.39
    ượt
    0.38
    єкт
    0.37
    в
    0.37
    스
    0.37
    Act Density 0.001%

    No Known Activations