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

    Neuronpedia

    INDEX
    Explanations

    cards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HW
    -0.07
    (:
    -0.06
     Manga
    -0.06
     ########
    -0.06
     Kidd
    -0.06
     recommand
    -0.06
     jente
    -0.06
    >${
    -0.06
    ('\\
    -0.06
    (',
    -0.06
    POSITIVE LOGITS
     nuest
    0.07
    итуа
    0.07
     synagogue
    0.06
    无码
    0.06
    abit
    0.06
     التف
    0.06
    Tel
    0.06
     กรกฎ
    0.06
    "N
    0.06
    reibung
    0.06
    Act Density 0.006%

    No Known Activations