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

    Neuronpedia

    INDEX
    Explanations

    making you feel better

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ব্ধ
    0.41
     பிரமி
    0.40
    fas
    0.39
    yati
    0.39
     शौ
    0.39
    freedom
    0.38
    深度
    0.37
     respect
    0.37
    ⵃ
    0.36
     fascinating
    0.36
    POSITIVE LOGITS
     brighten
    1.75
     brightening
    1.67
     cheer
    1.62
     cheered
    1.52
     uplifting
    1.48
     uplift
    1.45
     Cheer
    1.39
     cheering
    1.38
     cheerful
    1.34
     cheery
    1.30
    Act Density 0.068%

    No Known Activations