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

    Neuronpedia

    INDEX
    Explanations

    happy birthday

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亅
    0.44
    超过
    0.44
    第一
    0.43
     профессии
    0.41
    快
    0.41
    观
    0.40
    PROF
    0.40
    otification
    0.39
    WORTH
    0.38
    Easy
    0.38
    POSITIVE LOGITS
     materially
    0.45
    )=\
    0.45
     heim
    0.41
     Hild
    0.41
    )$.
    0.40
    }"
    0.40
    <unused408>
    0.40
     Curt
    0.39
     Pond
    0.39
     afflicted
    0.39
    Act Density 0.001%

    No Known Activations