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

    Neuronpedia

    INDEX
    Explanations

    Did, did, DID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不算
    0.72
    상은
    0.60
    accom
    0.60
     accomod
    0.56
    เป็นการ
    0.54
     summarise
    0.53
    认为是
    0.53
     Accom
    0.52
     محک
    0.52
     descre
    0.52
    POSITIVE LOGITS
    Did
    2.74
     did
    2.66
     Did
    2.63
    did
    2.38
     DID
    2.06
    DID
    1.90
     didn
    1.67
    你知道
    1.50
     Didn
    1.42
    didn
    1.36
    Act Density 0.185%

    No Known Activations