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

    Neuronpedia

    INDEX
    Explanations

    SQL FROM clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilov
    0.44
    év
    0.42
    ag
    0.42
    LOR
    0.42
    !='')
    0.42
    över
    0.42
    šem
    0.42
    !='
    0.41
    են
    0.39
    ('')
    0.39
    POSITIVE LOGITS
     `{
    0.42
     {};
    0.39
     androidx
    0.38
     detrimental
    0.36
    スペック
    0.36
     `
    0.36
    वाईसी
    0.36
     সজ্জিত
    0.36
     "";
    0.36
     kilobytes
    0.36
    Act Density 0.016%

    No Known Activations