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

    Neuronpedia

    INDEX
    Explanations

    digits after DON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hattam
    0.47
    黼
    0.40
     Oahu
    0.39
     Amtrak
    0.39
     amphibians
    0.39
     Eminem
    0.38
    t
    0.37
     Scientology
    0.36
    ងារ
    0.35
     Maser
    0.35
    POSITIVE LOGITS
    :
    0.47
    ات
    0.45
    0.44
    7
    0.42
    6
    0.42
    ↵↵
    0.40
    的東西
    0.40
     quale
    0.40
    ме
    0.39
    の見
    0.38
    Act Density 0.001%

    No Known Activations