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

    Neuronpedia

    INDEX
    Explanations

    foreign characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <b>
    0.41
    RBI
    0.40
    崛起
    0.40
     பகு
    0.39
    Article
    0.39
    Businesses
    0.39
     ك
    0.39
    Hyper
    0.38
    SEO
    0.38
    Indian
    0.38
    POSITIVE LOGITS
    ലെസ്
    0.47
     nurse
    0.46
    ৃতা
    0.44
    সমান
    0.41
     stoichi
    0.41
    थुरा
    0.41
    óz
    0.40
     diarrhoea
    0.40
     conserva
    0.40
     radia
    0.40
    Act Density 0.001%

    No Known Activations