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

    Neuronpedia

    INDEX
    Explanations

    frequently occurring words in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inglés
    0.41
    Bernard
    0.38
    คองโก
    0.37
    brite
    0.37
     Louisville
    0.36
    Joseph
    0.36
    ~~
    0.36
     Brodie
    0.35
     शाह
    0.35
    QFont
    0.35
    POSITIVE LOGITS
     LI
    0.56
    ⃣
    0.49
    ️⃣
    0.49
    LI
    0.47
     Li
    0.44
     itemList
    0.41
    nze
    0.39
     ಮಾಡ
    0.38
     zipper
    0.38
     품
    0.37
    Act Density 0.000%

    No Known Activations