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

    Neuronpedia

    INDEX
    Explanations

    TechCrunch article

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roma
    1.03
    सि
    1.02
    (-
    1.01
    ทาง
    1.00
    தால்
    0.97
    de
    0.96
    Đ
    0.94
    ([],
    0.93
     unto
    0.93
     bờ
    0.93
    POSITIVE LOGITS
     magazine
    2.57
     magazines
    2.50
     Magazine
    2.25
     newspapers
    2.09
     newspaper
    2.07
    杂志
    2.05
     Magazines
    2.02
     editorial
    1.92
     Newspapers
    1.87
     editorials
    1.85
    Act Density 0.256%

    No Known Activations