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

    Neuronpedia

    INDEX
    Explanations

    pygame initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.39
     June
    0.38
    Note
    0.38
     purpose
    0.37
    Purpose
    0.37
     March
    0.37
    做一个
    0.37
    5
    0.37
     You
    0.35
    purpose
    0.35
    POSITIVE LOGITS
    ológicos
    0.45
     각종
    0.44
     excepciones
    0.42
     généraux
    0.42
    Назад
    0.41
     системой
    0.41
    aży
    0.40
     nadi
    0.40
     adhere
    0.40
     สื
    0.40
    Act Density 0.012%

    No Known Activations