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

    Neuronpedia

    INDEX
    Explanations

    Rio de

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ⰽ
    -0.09
     commit
    -0.07
     sophistication
    -0.07
     cadre
    -0.07
     toc
    -0.06
     confidentiality
    -0.06
    召
    -0.06
     consciousness
    -0.06
     Sgt
    -0.06
     Arthur
    -0.06
    POSITIVE LOGITS
    清淡
    0.08
    Away
    0.07
    אווירה
    0.07
    PHPExcel
    0.07
     tub
    0.07
     nowrap
    0.07
     obligatory
    0.07
    -esque
    0.06
    呙
    0.06
    لا
    0.06
    Act Density 0.002%

    No Known Activations