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

    Neuronpedia

    INDEX
    Explanations

    fashion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     health
    -0.08
    `)↵
    -0.08
    管理者
    -0.07
    }
↵
    -0.07
    عزي
    -0.07
    `,↵
    -0.07
     heightFor
    -0.07
    卖家
    -0.07
    底蕴
    -0.07
    ","");↵
    -0.07
    POSITIVE LOGITS
    غو
    0.08
     bf
    0.08
    没啥
    0.07
    phans
    0.07
     Sears
    0.07
    cial
    0.07
     Antoine
    0.07
    /load
    0.07
    塵
    0.07
    -q
    0.07
    Act Density 0.064%

    No Known Activations