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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ürger
    -0.07
     �
    -0.07
    olulu
    -0.06
    497
    -0.06
     swelling
    -0.06
    (theta
    -0.06
    Buy
    -0.06
    istic
    -0.06
     sensory
    -0.06
    玉
    -0.06
    POSITIVE LOGITS
    Ệ
    0.07
     Listings
    0.07
     beans
    0.06
    ите
    0.06
    732
    0.06
     Báo
    0.06
    ChartData
    0.06
     الجم
    0.06
     futile
    0.06
     edecek
    0.06
    Act Density 0.023%

    No Known Activations