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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    helm
    -0.07
    .AddComponent
    -0.07
     McKay
    -0.06
     أث
    -0.06
     مستقیم
    -0.06
    izzas
    -0.06
    .Column
    -0.06
    .Mail
    -0.06
     Dirt
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    788
    0.07
    多少
    0.06
     subpo
    0.06
     exporter
    0.06
    790
    0.06
     inexp
    0.06
     Fen
    0.06
    攝
    0.06
     swamp
    0.06
    tep
    0.06
    Act Density 0.010%

    No Known Activations