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

    Neuronpedia

    INDEX
    Explanations

    web addresses and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /.
    0.34
    ().
    0.33
     absent
    0.33
     furthering
    0.32
    .
    0.31
     magazines
    0.31
    Trying
    0.30
    0.30
     preventative
    0.30
    (
    0.30
    POSITIVE LOGITS
    herokuapp
    0.46
    eu
    0.45
    info
    0.43
    net
    0.43
     eu
    0.43
     io
    0.42
    github
    0.39
    readthedocs
    0.38
    netlify
    0.38
    io
    0.37
    Act Density 0.013%

    No Known Activations