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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases that include the word "on"

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

    being on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxDecoration
    -0.51
     initComponents
    -0.47
    <mask>
    -0.45
    tispiece
    -0.44
    請問
    -0.43
    ViewInit
    -0.41
    mbggenerated
    -0.41
    MockMvc
    -0.41
     sacrificio
    -0.41
     astore
    -0.40
    POSITIVE LOGITS
     cherchés
    0.46
    出版年
    0.45
    AddTagHelper
    0.43
     Efq
    0.43
     Majefty
    0.43
    encodeWith
    0.42
     Catalana
    0.41
     AssemblyVersion
    0.40
     المعيارى
    0.40
    tiktok
    0.39
    Act Density 0.029%

    No Known Activations