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

    Neuronpedia

    INDEX
    Explanations

    programming concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     మూ
    0.70
    halo
    0.69
    Net
    0.68
     আকারের
    0.66
    сько
    0.65
     petites
    0.65
    >′</
    0.65
    kum
    0.64
    رآ
    0.64
     bandes
    0.64
    POSITIVE LOGITS
     чер
    0.65
    监测
    0.65
     monitoring
    0.62
     IList
    0.62
    బ
    0.61
    verticalLayout
    0.61
     slider
    0.61
    逻辑
    0.61
    ानिस्तान
    0.60
    दय
    0.59
    Act Density 0.005%

    No Known Activations