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

    Neuronpedia

    INDEX
    Explanations

    points related to concealment and restrictions of information

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

    Chinese characters related to "hide" or "hidden"

    np_acts-logits-general · gemini-2.0-flash

    hidden / 隠藏 / 厳しく

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MenuView
    -0.65
     Italijanski
    -0.64
    WindowConstants
    -0.64
    TemporalType
    -0.63
    GEBURTSDATUM
    -0.59
    richTextPanel
    -0.58
    Demografie
    -0.58
    WireFormat
    -0.57
    ंदीखरीदारी
    -0.57
     AssemblyProduct
    -0.56
    POSITIVE LOGITS
     vœux
    0.63
    %")
    0.57
     Betracht
    0.55
    uxta
    0.54
     genoux
    0.53
    〮
    0.53
     jambes
    0.53
    thesis
    0.53
    %");
    0.52
     Kand
    0.51
    Act Density 0.060%

    No Known Activations