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

    Neuronpedia

    INDEX
    Explanations

    Cole, admin, Art, French, 5

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.44
    墘
    0.42
    이나
    0.41
    alne
    0.41
    ,
    0.40
    8
    0.39
    Punk
    0.38
    ↵↵
    0.38
    Tw
    0.38
     पांडे
    0.38
    POSITIVE LOGITS
     kommt
    0.48
     മന്ത്രി
    0.48
    ချင်း
    0.48
     yarış
    0.48
    ক্ষেত্র
    0.47
     kommen
    0.46
     kuris
    0.45
     dieses
    0.45
     hastalık
    0.45
    たる
    0.44
    Act Density 0.335%

    No Known Activations