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

    Neuronpedia

    INDEX
    Explanations

    specific descriptions or qualifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ton
    0.54
    mills
    0.49
     ინტერ
    0.49
     realiz
    0.45
    rapid
    0.45
    ron
    0.44
    ប្រស
    0.44
     mils
    0.43
    mill
    0.43
     আর্থিক
    0.41
    POSITIVE LOGITS
     Specifically
    0.48
    ي
    0.47
    ं
    0.46
     Dock
    0.45
    ൫
    0.45
    ادة
    0.44
    ENCED
    0.44
    齒
    0.44
     właśnie
    0.43
    ز
    0.43
    Act Density 0.001%

    No Known Activations