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

    Neuronpedia

    INDEX
    Explanations

    scientific notation or list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    উদাহরণ
    0.49
    ཌ
    0.48
    ྥ
    0.48
    உங்கள்
    0.47
    եք
    0.47
    에
    0.46
    +#+#+
    0.46
    滟
    0.46
    டுத்து
    0.45
    煐
    0.45
    POSITIVE LOGITS
     {
    0.56
     (
    0.44
    pl
    0.41
    ){
    0.40
    mp
    0.40
    st
    0.39
     )
    0.38
     appropriate
    0.38
     Sang
    0.37
    ve
    0.37
    Act Density 0.004%

    No Known Activations