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

    Neuronpedia

    INDEX
    Explanations

    article or outline request

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    administrat
    0.44
    ignment
    0.42
    మన
    0.42
    credit
    0.42
    investment
    0.42
    initiated
    0.41
    issenschaft
    0.41
    adem
    0.41
    skar
    0.41
    ვნ
    0.40
    POSITIVE LOGITS
     expresses
    0.46
     જેમાં
    0.45
     calendars
    0.45
     expressing
    0.44
     Ensures
    0.44
     conveying
    0.44
     suppliers
    0.43
     Halloween
    0.41
     Deportes
    0.41
     ensure
    0.40
    Act Density 0.005%

    No Known Activations