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

    Neuronpedia

    INDEX
    Explanations

    has/have been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.26
     (
    0.24
     when
    0.23
     如果
    0.23
    r
    0.23
    0
    0.22
     from
    0.21
     ，
    0.21
    ，
    0.21
     ("
    0.20
    POSITIVE LOGITS
     been
    0.52
    been
    0.43
     BEEN
    0.42
     Been
    0.37
    Been
    0.34
     ollut
    0.33
     sido
    0.31
     været
    0.29
     olnud
    0.29
     été
    0.26
    Act Density 0.338%

    No Known Activations