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

    Neuronpedia

    INDEX
    Explanations

    a/an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     men
    -0.07
    Sie
    -0.06
    shortcode
    -0.06
     označ
    -0.06
     Variant
    -0.06
    Uri
    -0.06
    商
    -0.06
     مبار
    -0.06
     Shen
    -0.06
    ride
    -0.06
    POSITIVE LOGITS
    affe
    0.08
    lington
    0.07
     reinstall
    0.06
    (en
    0.06
    サービス
    0.06
    .xx
    0.06
     :)↵↵
    0.06
    getic
    0.06
     geil
    0.06
    취
    0.06
    Act Density 0.025%

    No Known Activations