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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obligations and expectations

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

    do not expect or assume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.67
    afficheront
    -0.60
     հղումներ
    -0.60
     ProtoMessage
    -0.56
     AssemblyCulture
    -0.54
     ComVisible
    -0.52
    tagHelperRunner
    -0.52
    Datuak
    -0.52
    AnimationsModule
    -0.52
     iNdEx
    -0.51
    POSITIVE LOGITS
     TextAppearance
    0.41
     teas
    0.33
     خبر
    0.33
    Lịch
    0.31
    SuspendLayout
    0.30
    getExternal
    0.30
    ImageIO
    0.30
    Lost
    0.30
    CAN
    0.30
     WR
    0.29
    Act Density 0.132%

    No Known Activations