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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    教师
    -0.07
    ovém
    -0.06
    -Star
    -0.06
     IPP
    -0.06
    WG
    -0.06
     Studi
    -0.06
    EventData
    -0.06
     Chính
    -0.06
     Combined
    -0.06
     дві
    -0.06
    POSITIVE LOGITS
     autor
    0.07
     ini
    0.07
     grac
    0.07
     wise
    0.06
     nicely
    0.06
    ses
    0.06
     ozone
    0.06
    .Info
    0.06
     soci
    0.06
     kus
    0.06
    Act Density 0.050%

    No Known Activations