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

    Neuronpedia

    INDEX
    Explanations

    Units of measure and currencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réuss
    2.17
    ير
    1.84
     τις
    1.78
    ok
    1.77
     کرام
    1.77
    ש
    1.77
    ité
    1.75
    این
    1.75
     liné
    1.75
    Golem
    1.75
    POSITIVE LOGITS
    ع
    2.13
     দাঁড়
    2.02
    npmjs
    1.98
    y
    1.91
    inafter
    1.83
    ৮
    1.82
    נו
    1.80
    𝓽
    1.79
    pèce
    1.78
    িয়াই
    1.77
    Act Density 0.194%

    No Known Activations