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

    Neuronpedia

    INDEX
    Explanations

    expectations or requests to me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्वे
    0.47
     стреми
    0.42
     огром
    0.41
     costitu
    0.39
     שנה
    0.38
    갖
    0.38
     desarrollando
    0.38
     עבור
    0.38
    olgens
    0.37
    rün
    0.37
    POSITIVE LOGITS
     mnie
    0.55
     me
    0.50
     আমাকে
    0.50
    讓我
    0.49
    আমাকে
    0.49
    让我
    0.47
     मुझ
    0.46
     ask
    0.46
     என்னை
    0.44
    和我
    0.44
    Act Density 0.469%

    No Known Activations