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

    Neuronpedia

    INDEX
    Explanations

    decrypt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ő
    -0.07
    權益
    -0.07
     Nuevo
    -0.07
     Każdy
    -0.07
    🎴
    -0.07
     Ricky
    -0.07
     Neg
    -0.07
     Educación
    -0.06
     cazzo
    -0.06
     Network
    -0.06
    POSITIVE LOGITS
     meats
    0.07
    接触
    0.07
    matter
    0.07
     rpm
    0.07
    🄲
    0.07
    关键词
    0.07
    راحة
    0.07
    unken
    0.06
    Chars
    0.06
    𝖏
    0.06
    Act Density 0.004%

    No Known Activations