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

    Neuronpedia

    INDEX
    Explanations

    parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raspberry
    -0.08
    AMY
    -0.07
    climate
    -0.07
    蔈
    -0.07
    .setStyle
    -0.07
     `,
    -0.07
    ipay
    -0.07
    螫
    -0.07
    鼍
    -0.07
     inflater
    -0.06
    POSITIVE LOGITS
    .generator
    0.07
    /c
    0.07
    Them
    0.07
    帶
    0.07
     Deal
    0.07
    objective
    0.07
     Actually
    0.06
     Goods
    0.06
     players
    0.06
    Sk
    0.06
    Act Density 0.003%

    No Known Activations