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

    Neuronpedia

    INDEX
    Explanations

    names, particularly those that appear frequently in author citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Zacharova, Servusova

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     times
    -0.36
    LogService
    -0.32
     zes
    -0.31
     magazines
    -0.31
    GenerationType
    -0.31
    koc
    -0.29
    simos
    -0.29
     conviene
    -0.28
     dost
    -0.28
     friendships
    -0.28
    POSITIVE LOGITS
    tanleria
    0.67
     surla
    0.65
    ronpa
    0.59
     henvisninger
    0.57
    preduce
    0.55
    SpringRunner
    0.55
     otomatig
    0.54
     tiguan
    0.53
     CreateTagHelper
    0.52
     zijne
    0.52
    Act Density 0.019%

    No Known Activations