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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Petra
    -0.07
    灯笼
    -0.07
    曈
    -0.07
     noktası
    -0.06
     Jeffrey
    -0.06
     comenz
    -0.06
     Foto
    -0.06
     nuestras
    -0.06
     Recruitment
    -0.06
    佔
    -0.06
    POSITIVE LOGITS
    과장
    0.08
    ḷ
    0.07
     sources
    0.07
    賢
    0.07
    getQuery
    0.07
    getOrElse
    0.07
     chiều
    0.07
    (World
    0.07
    ApplicationBuilder
    0.07
     evaluations
    0.07
    Act Density 0.232%

    No Known Activations