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

    Neuronpedia

    INDEX
    Explanations

    welcoming phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nghĩ
    0.43
     honestly
    0.42
     nossa
    0.40
     সেটাই
    0.37
    我覺得
    0.36
     denkt
    0.36
     திட்டம்
    0.35
     nosso
    0.35
    ...”
    0.35
     nasze
    0.35
    POSITIVE LOGITS
     гр
    0.49
    Visitors
    0.49
    Winner
    0.43
    Collect
    0.43
    Attendees
    0.43
     вой
    0.42
    ण्ट
    0.42
    Visitor
    0.41
    Gather
    0.41
    ｫ
    0.41
    Act Density 0.074%

    No Known Activations