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

    Neuronpedia

    INDEX
    Explanations

    check

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sayings
    -0.09
    جات
    -0.08
    .populate
    -0.08
     Dalam
    -0.08
    Configurator
    -0.07
    롤
    -0.07
    될
    -0.07
    meric
    -0.07
     promulg
    -0.07
    Essential
    -0.07
    POSITIVE LOGITS
    是否
    0.12
     जांच
    0.12
     是否
    0.11
     পরীক্ষা
    0.11
     überprüfen
    0.11
     обнаруж
    0.11
     দেখি
    0.11
     Провер
    0.10
     দেখে
    0.10
     controleren
    0.10
    Act Density 0.073%

    No Known Activations