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

    Neuronpedia

    INDEX
    Explanations

    John

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     libertin
    -0.07
    @js
    -0.06
     itibar
    -0.06
     Doming
    -0.06
    けない
    -0.06
    Vis
    -0.06
     برخورد
    -0.06
    Capt
    -0.06
    _interest
    -0.06
     contentType
    -0.06
    POSITIVE LOGITS
    inson
    0.07
    ۵
    0.06
    [column
    0.06
     principles
    0.06
     mediums
    0.06
    faces
    0.06
    /ad
    0.06
    ARED
    0.06
    .LogInformation
    0.06
    naire
    0.06
    Act Density 0.006%

    No Known Activations