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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user actions and their impact or significance

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

    both ... and .

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.51
    GEBURTSDATUM
    -0.48
    WriteTagHelper
    -0.47
     onBackPressed
    -0.43
     تضيفلها
    -0.43
    engesch
    -0.42
    expandindo
    -0.42
     createDate
    -0.41
     ddelweddau
    -0.41
     lainnya
    -0.41
    POSITIVE LOGITS
    owohl
    0.52
     Both
    0.44
    ագրություններ
    0.44
    Both
    0.44
    הערות
    0.43
    tilhe
    0.42
     سكانية
    0.40
    Neither
    0.40
    ſelves
    0.40
    tagHelperRunner
    0.39
    Act Density 0.128%

    No Known Activations