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

    Neuronpedia

    INDEX
    Explanations

    severity/priority

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adecimal
    -0.08
    عبد
    -0.07
    indow
    -0.07
    تسجيل
    -0.07
     Những
    -0.07
    �
    -0.07
    webpack
    -0.07
     Feedback
    -0.07
    .selectedIndex
    -0.07
    (nr
    -0.07
    POSITIVE LOGITS
     joked
    0.07
     correction
    0.07
     projet
    0.07
     *>
    0.07
    ဋ
    0.07
     замеча
    0.07
    먀
    0.07
     замет
    0.07
    PE
    0.06
     th
    0.06
    Act Density 0.011%

    No Known Activations