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

    Neuronpedia

    INDEX
    Explanations

    lecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kirby
    -0.08
     учиты
    -0.07
    اسو
    -0.07
    ுள்ளதாக
    -0.07
     lil
    -0.07
     usernames
    -0.07
     Spiel
    -0.07
     अक्ष
    -0.07
     след
    -0.07
     Brushes
    -0.07
    POSITIVE LOGITS
     lectures
    0.11
    /tutorial
    0.09
     듣
    0.09
     Notre
    0.08
     sobre
    0.08
    讲
    0.08
    体系
    0.08
     лек
    0.08
    厅
    0.08
     halls
    0.08
    Act Density 0.008%

    No Known Activations