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

    Neuronpedia

    INDEX
    Explanations

    median / average definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yli
    0.98
    俄
    0.91
     copyrighted
    0.90
    об
    0.90
    view
    0.88
     Russia
    0.87
    decode
    0.86
     I
    0.86
     liberties
    0.85
    级
    0.85
    POSITIVE LOGITS
     pulang
    1.12
     ઘર
    1.04
    ܨ
    0.99
    вата
    0.99
    라
    0.97
    내
    0.97
     возь
    0.92
     공연
    0.92
     polov
    0.91
    ಂಪ
    0.91
    Act Density 0.000%

    No Known Activations