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

    Neuronpedia

    INDEX
    Explanations

    special characters surrounded by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ิ
    0.45
    ा
    0.45
     TRANSPORTURI
    0.44
    讠
    0.43
    с
    0.43
    玼
    0.42
    壹章
    0.41
    ล์
    0.40
     ी
    0.40
    eus
    0.40
    POSITIVE LOGITS
     three
    0.51
     drinks
    0.48
     four
    0.46
    0.46
     five
    0.46
     two
    0.46
     veggies
    0.45
     shaman
    0.45
     side
    0.45
     foods
    0.44
    Act Density 0.003%

    No Known Activations