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

    Neuronpedia

    INDEX
    Explanations

    ~~

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有限责任
    -0.07
    娴
    -0.07
     ز
    -0.06
     współ
    -0.06
    nty
    -0.06
     fields
    -0.06
     fict
    -0.06
     испол
    -0.06
    巡
    -0.06
    だ
    -0.06
    POSITIVE LOGITS
     nắng
    0.07
     loving
    0.07
    ações
    0.07
    𝗲
    0.07
     liquidity
    0.07
     honorable
    0.07
     username
    0.07
    团结
    0.06
     herbs
    0.06
    开元棋牌
    0.06
    Act Density 0.002%

    No Known Activations