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

    Neuronpedia

    INDEX
    Explanations

    domain name suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    平台的
    0.26
     ofrecemos
    0.25
    RatingDiff
    0.25
    כּ
    0.25
    老
    0.24
     הז
    0.24
    0.24
     уйна
    0.24
    ꔹ
    0.24
    хбет
    0.24
    POSITIVE LOGITS
    org
    0.52
     org
    0.48
     com
    0.41
     gov
    0.39
    gov
    0.38
    edu
    0.35
    com
    0.34
     edu
    0.32
     government
    0.30
     Org
    0.30
    Act Density 0.004%

    No Known Activations