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

    Neuronpedia

    INDEX
    Explanations

    Say 'the' or 'train'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ency
    -0.09
    Each
    -0.08
    encies
    -0.08
    ences
    -0.08
    �
    -0.08
    Prin
    -0.07
     sumar
    -0.07
    quettes
    -0.07
    ensions
    -0.07
    ux
    -0.07
    POSITIVE LOGITS
     ребенка
    0.09
     approaching
    0.09
     фильма
    0.08
    0.08
    ของ
    0.08
     камеры
    0.08
     вашего
    0.08
     laden
    0.08
     yerləş
    0.08
     карты
    0.08
    Act Density 0.005%
    No Known Activations