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

    Neuronpedia

    INDEX
    Explanations

    state administration

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     değişiklik
    0.55
    atı
    0.54
     الفيزياء
    0.54
     elves
    0.54
     Elke
    0.54
     bieden
    0.53
    ила
    0.53
     cabs
    0.52
    Neben
    0.52
     Elle
    0.52
    POSITIVE LOGITS
    administrative
    0.63
     trigo
    0.61
    政府采购
    0.59
     State
    0.56
     ";
    0.56
     тра
    0.56
     государственной
    0.56
    uterine
    0.56
    operational
    0.56
    カー
    0.55
    Act Density 0.001%

    No Known Activations