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

    Neuronpedia

    INDEX
    Explanations

    names and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >
    0.33
    ņa
    0.31
    ilers
    0.31
    al
    0.31
    és
    0.30
    ério
    0.30
    ūn
    0.30
    （
    0.30
     Geschäftsführer
    0.30
     >
    0.29
    POSITIVE LOGITS
     العديد
    0.37
     UFC
    0.35
     FaceTime
    0.35
     اختبار
    0.33
     Polski
    0.33
     Beirut
    0.33
     Wszyst
    0.33
     Oahu
    0.32
     هذه
    0.32
     Zumba
    0.32
    Act Density 0.000%

    No Known Activations