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

    Neuronpedia

    INDEX
    Explanations

    code and logic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ম্প
    0.77
     Tyre
    0.70
    Aye
    0.69
    Meat
    0.69
    Able
    0.68
    Writable
    0.67
     cheerful
    0.67
     Furious
    0.67
     loos
    0.63
     carelessly
    0.63
    POSITIVE LOGITS
    zent
    0.84
     ঘনত্ব
    0.75
     whatsapp
    0.71
     আসিয়া
    0.71
    TOOLBAR
    0.71
    ளால்
    0.70
     critères
    0.70
     E
    0.69
     নিঃ
    0.69
     iş
    0.69
    Act Density 0.000%

    No Known Activations