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

    Neuronpedia

    INDEX
    Explanations

    Latin origin, etymology, meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Сурикова
    0.40
    ！！！
    0.39
     النسبيه
    0.39
    𒌅
    0.38
     كوساين
    0.38
    🗾
    0.37
     المثلثيه
    0.37
    🩰
    0.37
    ಬೇವಿನ
    0.37
    িনবার্গ
    0.36
    POSITIVE LOGITS
    0.44
     "
    0.39
    ↵
    0.38
     (
    0.38
    ,
    0.38
    J
    0.37
     L
    0.37
     the
    0.37
    h
    0.37
     son
    0.36
    Act Density 0.075%

    No Known Activations