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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    נב
    -0.07
    千年
    -0.07
    iel
    -0.07
    bbe
    -0.07
    controlled
    -0.07
     القرن
    -0.06
     ejac
    -0.06
    坐着
    -0.06
    尽头
    -0.06
    уществ
    -0.06
    POSITIVE LOGITS
    ={{↵
    0.07
     Palette
    0.06
     medals
    0.06
    ألعاب
    0.06
     italic
    0.06
    avoid
    0.06
    І
    0.06
    .Registry
    0.06
    -routing
    0.06
    玙
    0.06
    Act Density 0.002%

    No Known Activations