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

    Neuronpedia

    INDEX
    Explanations

    Thank you notes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (All
    -0.08
    ähl
    -0.08
     skipped
    -0.08
    ntl
    -0.08
     /.
    -0.08
    짓
    -0.08
    只有
    -0.08
     mencari
    -0.07
    質
    -0.07
     состоит
    -0.07
    POSITIVE LOGITS
     "@/
    0.09
     جهود
    0.09
     सफल
    0.09
     '@/
    0.08
     excessive
    0.08
     সফল
    0.08
    Thank
    0.08
    THANK
    0.08
     उत्कृष्ट
    0.08
     quanto
    0.08
    Act Density 0.014%

    No Known Activations