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

    Neuronpedia

    INDEX
    Explanations

    September

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åĺ§
    -0.27
     PROP
    -0.24
    å¤Ń
    -0.24
    éĥ½æĥ³
    -0.24
     leo
    -0.23
    imated
    -0.23
     TTC
    -0.23
     QT
    -0.23
     ET
    -0.23
    .realm
    -0.23
    POSITIVE LOGITS
    å¼ıçļĦ
    0.27
    åIJĮæľŁ
    0.26
    ulent
    0.26
    nite
    0.24
    oons
    0.23
    anz
    0.23
    ivors
    0.23
    æĪijçĽ¸ä¿¡
    0.23
    ige
    0.23
    zie
    0.23
    Act Density 0.130%

    No Known Activations