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

    Neuronpedia

    INDEX
    Explanations

    stressful/tragic jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ár
    -0.07
     Clean
    -0.07
     hemisphere
    -0.07
    Grace
    -0.07
    ρά
    -0.07
    Netflix
    -0.06
     кур
    -0.06
     physicist
    -0.06
     TV
    -0.06
     Communications
    -0.06
    POSITIVE LOGITS
     dateFormatter
    0.07
    願い
    0.07
    LOAT
    0.06
     kutje
    0.06
     biod
    0.06
    월까지
    0.06
     EIF
    0.06
    .pending
    0.06
     щ
    0.05
    ickness
    0.05
    Act Density 0.050%

    No Known Activations