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

    Neuronpedia

    INDEX
    Explanations

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Analyser
    0.58
     جوړونکو
    0.56
     kullanılan
    0.54
     wymaga
    0.54
    Ž
    0.54
    MyISAM
    0.53
    ▍
    0.53
    ίζει
    0.52
     अडानी
    0.52
    ⟢
    0.51
    POSITIVE LOGITS
     Scrap
    0.57
    ash
    0.56
     възможно
    0.55
    ^+
    0.55
    ρε
    0.54
     ^
    0.54
     Tutorials
    0.54
     :
    0.53
    ρα
    0.53
     muffin
    0.53
    Act Density 0.019%

    No Known Activations