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

    Neuronpedia

    INDEX
    Explanations

    но

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    可靠
    -0.08
     plumbing
    -0.08
    éin
    -0.08
     renewable
    -0.08
    伙伴
    -0.07
    xref
    -0.07
     samm
    -0.07
     betrouwbare
    -0.07
     PSL
    -0.07
     prü
    -0.07
    POSITIVE LOGITS
     captivated
    0.10
     unforgettable
    0.09
     allure
    0.08
     subconscious
    0.08
    想着
    0.08
     impeccable
    0.08
     الصغيرة
    0.08
     unut
    0.08
     greeted
    0.08
     decreased
    0.08
    Act Density 0.004%

    No Known Activations