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

    Neuronpedia

    INDEX
    Explanations

    among people who

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Política
    1.19
    marshalN
    1.16
    Méd
    1.07
    Má
    1.04
    Accordion
    1.03
    Características
    1.01
    Tá
    1.01
    Fract
    1.00
    Dados
    0.99
    Subgraph
    0.99
    POSITIVE LOGITS
    </h3>
    1.79
     […]
    1.53
    ‬
    1.45
    </h1>
    1.42
     [...]
    1.37
    </h2>
    1.36
    </td>
    1.35
    <0x0D>
    1.34
    非常的
    1.30
     阅读全文
    1.27
    Act Density 3.250%

    No Known Activations