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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    顺德
    -0.07
     Yale
    -0.07
    Ặ
    -0.07
    -container
    -0.06
     Jesus
    -0.06
     amendment
    -0.06
    ism
    -0.06
    مل
    -0.06
    /code
    -0.06
    aur
    -0.06
    POSITIVE LOGITS
    expense
    0.08
     diarrhea
    0.07
    _end
    0.07
    Labor
    0.07
    ctrine
    0.07
     wing
    0.07
    )--
    0.06
    ้น
    0.06
    พฤศจ
    0.06
    🌙
    0.06
    Act Density 0.006%

    No Known Activations