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

    Neuronpedia

    INDEX
    Explanations

    online search terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Analyzing
    0.51
    Lymph
    0.51
    shaus
    0.50
    SplashScreen
    0.50
    মনসিংহ
    0.48
    пь
    0.47
    :$
    0.47
    欬
    0.47
    ISH
    0.46
    Glasgow
    0.46
    POSITIVE LOGITS
     search
    0.85
     searches
    0.77
     google
    0.74
    検索
    0.73
     searched
    0.69
     поиска
    0.66
     Google
    0.65
     zoek
    0.64
     શોધ
    0.64
     সার্চ
    0.64
    Act Density 0.117%

    No Known Activations