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

    Neuronpedia

    INDEX
    Explanations

    planning and creating documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    之称
    -0.08
    恂
    -0.08
    ANTE
    -0.07
    orio
    -0.07
    атег
    -0.07
    }@
    -0.07
    UPI
    -0.07
    arr
    -0.07
     vocabulary
    -0.07
    -inspired
    -0.07
    POSITIVE LOGITS
     convo
    0.07
     Dat
    0.07
    Fetch
    0.07
    itemid
    0.06
    帜
    0.06
    viewport
    0.06
    实事
    0.06
     OID
    0.06
     breastfeeding
    0.06
     threads
    0.06
    Act Density 0.125%

    No Known Activations