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

    Neuronpedia

    INDEX
    Explanations

    leading vacation rentals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    냇
    0.44
     oks
    0.43
    وق
    0.42
    蝴
    0.41
     lastname
    0.40
     задание
    0.39
    మయ్య
    0.38
     سارے
    0.38
    𒈨
    0.38
    SPACE
    0.38
    POSITIVE LOGITS
     rather
    0.45
    vective
    0.43
    iland
    0.43
     common
    0.41
     Reyn
    0.40
    go
    0.40
    sin
    0.39
     absolutely
    0.39
     court
    0.39
     go
    0.39
    Act Density 0.000%

    No Known Activations