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

    Neuronpedia

    INDEX
    Explanations

    phrases related to understanding context and implications in discussions

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

    knowing truths and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.81
    MigrationBuilder
    -0.64
     autorytatywna
    -0.63
    ItemBackground
    -0.63
    windowFixed
    -0.61
    mybatisplus
    -0.58
     SwitchCompat
    -0.58
     يتيمه
    -0.56
     BorderSide
    -0.56
    Personensuche
    -0.55
    POSITIVE LOGITS
    Ms
    0.35
    ValueStyle
    0.32
    üle
    0.31
    TabView
    0.30
     apparently
    0.29
     unknown
    0.28
    contentLoaded
    0.28
     Ms
    0.28
     BytesLike
    0.27
    СТВ
    0.27
    Act Density 0.112%

    No Known Activations