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

    Neuronpedia

    INDEX
    Explanations

    words emphasizing size or significance

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

    big, huge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DataAnnotations
    -0.58
    GraphicsUnit
    -0.57
    GEBURTSDATUM
    -0.53
    UrlResolution
    -0.50
     Electrode
    -0.47
     bellezza
    -0.46
     quoc
    -0.46
     Challenges
    -0.45
    fjspx
    -0.45
    ✢
    -0.45
    POSITIVE LOGITS
     fan
    0.39
     modelAndView
    0.34
     typelib
    0.34
     onData
    0.33
     apolog
    0.33
    mainWindow
    0.32
    gwt
    0.32
     Größen
    0.32
     kissing
    0.32
     liking
    0.32
    Act Density 0.013%

    No Known Activations