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

    Neuronpedia

    INDEX
    Explanations

    Angela Merkel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    铁路
    -0.06
     sincerely
    -0.06
     Drinking
    -0.06
     Ins
    -0.06
     remedies
    -0.06
     Sections
    -0.06
    但
    -0.06
    =key
    -0.06
    urv
    -0.06
    =↵↵
    -0.06
    POSITIVE LOGITS
    씨
    0.07
     depressive
    0.07
     ::::::::
    0.07
     condemnation
    0.07
    rač
    0.07
    \Notifications
    0.06
    uat
    0.06
    ury
    0.06
     setLoading
    0.06
     gamle
    0.06
    Act Density 0.006%

    No Known Activations