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

    Neuronpedia

    INDEX
    Explanations

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     შორის
    1.41
    এশিয়া
    1.38
     방정
    1.35
     인해
    1.34
    子女
    1.34
     planète
    1.30
     étroites
    1.29
    ázej
    1.27
     lze
    1.24
     البر
    1.23
    POSITIVE LOGITS
    t
    1.70
    ت
    1.69
    н
    1.65
    ve
    1.64
    re
    1.63
    ن
    1.63
    𝗹
    1.63
    us
    1.61
    دام
    1.61
    ל
    1.60
    Act Density 0.038%

    No Known Activations