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

    Neuronpedia

    INDEX
    Explanations

    opposition candidates and parties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    1.09
    不
    1.02
     hypothes
    0.98
    我
    0.92
     és
    0.91
     sozial
    0.89
     měla
    0.88
     chủ
    0.87
    会
    0.86
     have
    0.86
    POSITIVE LOGITS
    opposition
    1.13
     Opposition
    1.03
    ।
    1.02
    oppositions
    1.00
    ン
    0.98
    n
    0.98
    Ordinate
    0.96
     opposition
    0.95
    nbs
    0.95
    ानी
    0.94
    Act Density 0.001%

    No Known Activations