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

    Neuronpedia

    INDEX
    Explanations

    say "built"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timestamp
    -0.08
     gái
    -0.07
     Everybody
    -0.07
    と思って
    -0.07
    Watch
    -0.07
     StatefulWidget
    -0.07
    Boston
    -0.06
    isObject
    -0.06
     Employee
    -0.06
    atetime
    -0.06
    POSITIVE LOGITS
    Ḉ
    0.07
     completion
    0.07
     plaza
    0.07
    unal
    0.07
    倾
    0.07
    发放
    0.06
    .dd
    0.06
    :@"%@
    0.06
    .discount
    0.06
    삽
    0.06
    Act Density 0.137%

    No Known Activations