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

    Neuronpedia

    INDEX
    Explanations

    instead of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लगभग
    0.46
     ആരംഭ
    0.41
     extremamente
    0.41
    ようになる
    0.40
    এই
    0.40
     mittlerweile
    0.40
    此同时
    0.39
     შემდეგ
    0.38
    תר
    0.38
     রয়েছে
    0.38
    POSITIVE LOGITS
     instead
    0.78
     вместо
    0.77
     대신
    0.77
    instead
    0.74
    Instead
    0.72
    代わりに
    0.66
     Instead
    0.66
     invece
    0.62
     பதிலாக
    0.61
     statt
    0.61
    Act Density 0.068%

    No Known Activations