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

    Neuronpedia

    INDEX
    Explanations

    describing styles of communication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ாதாரண
    0.47
    几种
    0.45
    滟
    0.45
    дени
    0.44
     ефектив
    0.44
     Handwriting
    0.43
    வதற்கான
    0.43
     查询
    0.42
     आरोपों
    0.42
    barang
    0.41
    POSITIVE LOGITS
    を防
    0.43
    別
    0.43
    LOOP
    0.42
     thereby
    0.41
     manure
    0.41
    性を
    0.41
    ZIP
    0.41
    CONTIN
    0.40
     chop
    0.39
     preven
    0.39
    Act Density 0.009%

    No Known Activations