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

    Neuronpedia

    INDEX
    Explanations

    written

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Elijah
    0.53
     Ernest
    0.52
     Elinor
    0.52
     observant
    0.51
     isAdmin
    0.51
     Emma
    0.50
    ్‌
    0.50
    =$\
    0.49
    гна
    0.49
     Verona
    0.48
    POSITIVE LOGITS
     ط
    0.55
     औष
    0.53
    akat
    0.53
     تقویت
    0.53
     س
    0.52
    uddh
    0.51
     مش
    0.50
     ساز
    0.50
     آ
    0.50
    ogens
    0.50
    Act Density 0.000%

    No Known Activations