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

    Neuronpedia

    INDEX
    Explanations

    mentioning family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newInput
    0.71
     panties
    0.57
    डेट
    0.57
    PointerException
    0.56
     вершин
    0.55
    baidu
    0.55
     ಥ
    0.55
    ChatGPT
    0.54
    ahraga
    0.54
    Debug
    0.54
    POSITIVE LOGITS
     family
    6.35
    family
    5.78
    Family
    5.70
     Family
    5.64
     families
    5.56
     família
    5.18
     famiglia
    5.13
     familia
    5.10
     Families
    5.04
     FAMILY
    5.03
    Act Density 0.192%

    No Known Activations