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

    Neuronpedia

    INDEX
    Explanations

    discussing Ant Design Avatar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਫ਼
    0.51
    စ္
    0.48
     condensing
    0.47
    ０
    0.46
     pavatt
    0.46
    匏
    0.46
     picnics
    0.46
    뉜
    0.45
    ڦ
    0.45
    럇
    0.45
    POSITIVE LOGITS
    வலி
    0.42
    Shan
    0.41
     بيد
    0.41
    iele
    0.39
    äude
    0.39
    ilever
    0.38
    ire
    0.37
     হাতের
    0.37
     darunter
    0.37
    Shore
    0.37
    Act Density 0.003%

    No Known Activations