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

    Neuronpedia

    INDEX
    Explanations

    You

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pow
    -0.07
    755
    -0.07
     Emil
    -0.07
     Rhodes
    -0.07
     сбор
    -0.06
     протяж
    -0.06
    建议
    -0.06
     María
    -0.06
     Channels
    -0.06
     مشار
    -0.06
    POSITIVE LOGITS
     mới
    0.07
    努
    0.07
     You
    0.06
    you
    0.06
     thanked
    0.06
     you
    0.06
     OSC
    0.06
    Ş
    0.06
    ��
    0.06
    turn
    0.06
    Act Density 0.042%

    No Known Activations