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

    Neuronpedia

    INDEX
    Explanations

    focuses solely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aprend
    0.42
     stride
    0.41
     सीखना
    0.41
     learn
    0.41
    學
    0.40
    풀
    0.39
    LEAR
    0.39
     LEAR
    0.39
    跄
    0.38
     learning
    0.38
    POSITIVE LOGITS
     сатып
    0.40
     ప్రభుత్వం
    0.40
     Website
    0.40
     सेल्स
    0.39
    uração
    0.39
    Примечания
    0.38
    注
    0.38
    JsonPart
    0.37
     نوٹ
    0.37
     Frühstück
    0.37
    Act Density 0.001%

    No Known Activations