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

    Neuronpedia

    INDEX
    Explanations

    complaint

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SizeMode
    -0.07
    tracks
    -0.07
    (sequence
    -0.06
    795
    -0.06
     菲
    -0.06
    Russ
    -0.06
    .Fill
    -0.06
     Stock
    -0.06
    edn
    -0.06
    (work
    -0.06
    POSITIVE LOGITS
     complaint
    0.09
     complaints
    0.09
     Complaint
    0.07
     числа
    0.07
     لأ
    0.06
    astreet
    0.06
    Comparator
    0.06
     pestic
    0.06
     vulnerability
    0.06
     Weapons
    0.06
    Act Density 0.006%

    No Known Activations