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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oder
    -0.08
     सत
    -0.08
     లేదా
    -0.08
     또는
    -0.08
     किंवा
    -0.07
     বা
    -0.07
    　↵
    -0.07
     Nachricht
    -0.07
     transformational
    -0.07
     અથવા
    -0.07
    POSITIVE LOGITS
     luckily
    0.08
    ่า
    0.08
    CELLENT
    0.07
     inic
    0.07
    dang
    0.07
    Luckily
    0.07
    มี
    0.07
    Zip
    0.07
    kung
    0.07
    ง
    0.07
    Act Density 0.000%

    No Known Activations