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

    Neuronpedia

    INDEX
    Explanations

    multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    某个
    0.45
     bởi
    0.41
     Airbnb
    0.41
    memberName
    0.40
    烦
    0.39
     dotyczą
    0.39
    typeName
    0.39
    惩
    0.39
    困难
    0.38
    lastName
    0.38
    POSITIVE LOGITS
     jsou
    0.54
    Voici
    0.52
    Dieser
    0.52
    Hlav
    0.51
    was
    0.50
    Dieses
    0.50
    Diese
    0.50
    この
    0.49
    იან
    0.49
    這是
    0.48
    Act Density 0.010%

    No Known Activations