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

    Neuronpedia

    INDEX
    Explanations

    prejudicial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ment
    -0.08
    ");}↵
    -0.08
     Clarke
    -0.07
    .secondary
    -0.07
    .Person
    -0.07
    Mage
    -0.07
     }
    -0.07
     celebrates
    -0.07
     trivia
    -0.06
     romance
    -0.06
    POSITIVE LOGITS
    &
    0.07
    橱
    0.07
    如果我们
    0.07
    🕘
    0.07
    婌
    0.07
     junction
    0.07
    쏨
    0.06
    .Client
    0.06
     ihr
    0.06
    ﮭ
    0.06
    Act Density 0.004%

    No Known Activations