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

    Neuronpedia

    INDEX
    Explanations

    wallpaper

    np_max-act · gemini-2.0-flash

    This neuron activates strongly on terms referring to wallpapers or background images (e.g., “wallpaper,” “wallpapers,” “background”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .GetDirectoryName
    -0.06
    \Eloquent
    -0.06
    ';
↵
    -0.06
    atemala
    -0.06
    day
    -0.06
    .cleaned
    -0.06
    зя
    -0.05
    Day
    -0.05
    는다
    -0.05
     {\
    -0.05
    POSITIVE LOGITS
    _jet
    0.07
     Fuji
    0.07
    status
    0.07
    _pi
    0.06
     corporation
    0.06
     relation
    0.06
     наст
    0.06
     sanctions
    0.06
     luaL
    0.06
     банку
    0.06
    Act Density 0.004%

    No Known Activations