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

    Neuronpedia

    INDEX
    Explanations

    dogs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ра
    1.69
    لية
    1.59
     Beaucoup
    1.57
     mètres
    1.48
    る
    1.47
    ન
    1.47
     großer
    1.44
    BackColor
    1.42
    ID
    1.40
    nytimes
    1.37
    POSITIVE LOGITS
    ৪
    1.99
    То
    1.82
    ﺮ
    1.78
     Το
    1.77
    th
    1.75
    <0x8A>
    1.72
    कर
    1.70
     cisplatin
    1.70
    א
    1.70
    ﺤ
    1.69
    Act Density 0.015%

    No Known Activations