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

    Neuronpedia

    INDEX
    Explanations

    Time spans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tikang
    -1.15
     تضيفلها
    -1.07
    ImageContext
    -1.06
    GEBURTSDATUM
    -1.04
     propOrder
    -1.01
    IntoConstraints
    -1.00
     lenker
    -0.97
    InjectAttribute
    -0.97
     مشين
    -0.96
    ^(@)
    -0.95
    POSITIVE LOGITS
    ,
    0.59
    {
    0.59
    /
    0.58
    "
    0.57
    //
    0.56
    '
    0.54
    _
    0.53
    v
    0.52
    .
    0.52
     &
    0.51
    Act Density 0.057%

    No Known Activations