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

    Neuronpedia

    INDEX
    Explanations

    defining macros and constants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    א
    0.61
    é
    0.55
    d
    0.49
    ä
    0.46
    app
    0.46
    t
    0.46
    ப
    0.46
    اص
    0.45
    ور
    0.45
    情况
    0.45
    POSITIVE LOGITS
    Somos
    0.51
     svojim
    0.50
    zoeken
    0.49
    クトル
    0.48
    aduras
    0.47
     Всем
    0.46
     funziona
    0.46
     mumkin
    0.46
     Наши
    0.46
     प्रश्‍
    0.46
    Act Density 0.015%

    No Known Activations