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

    Neuronpedia

    INDEX
    Explanations

    reality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    );"
    -0.07
    网刊
    -0.07
    >');
↵
    -0.07
    ῆ
    -0.07
    }",↵
    -0.07
    )");↵
    -0.07
    '")↵
    -0.07
     Babe
    -0.07
    earth
    -0.06
    多少
    -0.06
    POSITIVE LOGITS
     Neg
    0.07
     deco
    0.06
    (lon
    0.06
     Dro
    0.06
     Aj
    0.06
     inex
    0.06
     NSLayoutConstraint
    0.06
     تلاش
    0.06
    +'\
    0.06
     gt
    0.06
    Act Density 0.827%

    No Known Activations