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

    Neuronpedia

    INDEX
    Explanations

    programming code imports and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TikTok
    0.96
     Tiktok
    0.92
    tiktok
    0.89
     tiktok
    0.87
    TikTok
    0.83
     코로나
    0.83
     lockdowns
    0.83
     DeSantis
    0.82
     NFTs
    0.81
     covid
    0.80
    POSITIVE LOGITS
    শিব
    0.69
     बरत
    0.65
    Ant
    0.64
    Tong
    0.62
    http
    0.62
    /****
    0.61
    રા
    0.60
     trà
    0.60
    Fang
    0.59
     bour
    0.59
    Act Density 0.009%

    No Known Activations