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

    Neuronpedia

    INDEX
    Explanations

    mpl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Мат
    -0.07
    ě
    -0.07
     cherry
    -0.07
    Bes
    -0.06
    yer
    -0.06
     hombre
    -0.06
    ٩
    -0.06
    uga
    -0.06
    unt
    -0.06
    什
    -0.06
    POSITIVE LOGITS
     실�
    0.08
     '_',
    0.07
    .GetOrdinal
    0.07
     tearDown
    0.07
    +/
    0.07
    性
    0.06
    >").
    0.06
    persist
    0.06
    TableRow
    0.06
    这一
    0.06
    Act Density 0.002%

    No Known Activations