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

    Neuronpedia

    INDEX
    Explanations

    [

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transcoding
    0.40
     ```
    0.39
     Laravel
    0.39
     shakespeare
    0.39
     lapply
    0.39
    ...."
    0.38
     django
    0.38
     gara
    0.38
     jquery
    0.38
     Mende
    0.38
    POSITIVE LOGITS
    i
    0.54
    _)
    0.54
    int
    0.48
    ,)
    0.45
     _)
    0.45
    num
    0.43
    ii
    0.41
    .)
    0.40
    len
    0.40
    Num
    0.40
    Act Density 0.218%

    No Known Activations