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

    Neuronpedia

    INDEX
    Explanations

    Nam or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     //@
    0.44
    ाल
    0.40
     agreeing
    0.39
    AssetsRequest
    0.39
    ementara
    0.38
    ิล
    0.38
    enario
    0.38
    OrderID
    0.37
    考虑到
    0.37
    TxtArea
    0.37
    POSITIVE LOGITS
     Nam
    0.51
    Nam
    0.44
    plate
    0.41
    spaced
    0.41
    ႉ
    0.41
     NAM
    0.40
    üten
    0.39
    ناسب
    0.39
     Nim
    0.38
     nam
    0.38
    Act Density 0.022%

    No Known Activations