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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax or structure

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

    Code snippets and some unusual words

    np_acts-logits-general · gemini-2.0-flash

    g followed by saponin/Gamma/Court

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.09
    GEBURTSDATUM
    -0.90
    PerformLayout
    -0.88
    tagHelperRunner
    -0.83
    PreferredItem
    -0.80
    addCriterion
    -0.80
     StringTokenizer
    -0.79
     المعيارى
    -0.78
    parsedMessage
    -0.77
    queryInterface
    -0.76
    POSITIVE LOGITS
     it
    0.51
    it
    0.44
    haft
    0.41
     vol
    0.40
     default
    0.39
     lé
    0.39
    hak
    0.39
     flu
    0.38
     But
    0.38
    عد
    0.38
    Act Density 0.053%

    No Known Activations