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

    Neuronpedia

    INDEX
    Explanations

    spotting or spot instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    el
    3.44
    ส์
    3.07
    र
    2.98
    или
    2.98
    comboBox
    2.79
     fillet
    2.73
    elves
    2.72
     wafers
    2.68
    ֲ
    2.66
     посмотреть
    2.61
    POSITIVE LOGITS
    ्स
    4.47
    tttt
    3.07
    ting
    2.98
    tted
    2.87
    습니다
    2.76
    ೂರ್ವ
    2.75
    ات
    2.72
    ್ಣ
    2.70
    પણે
    2.69
    色列
    2.69
    Act Density 0.039%

    No Known Activations