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

    Neuronpedia

    INDEX
    Explanations

    quantity of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    どのような
    0.50
    どの
    0.45
    版本
    0.45
    までの
    0.45
    求解
    0.40
    Какой
    0.40
    版本的
    0.39
     ఎలాంటి
    0.39
    icket
    0.39
    するという
    0.39
    POSITIVE LOGITS
     things
    2.05
     cosas
    1.77
     coisas
    1.62
     thing
    1.59
    things
    1.59
     چیز
    1.58
     Things
    1.45
    Things
    1.45
     चीजें
    1.41
     вещи
    1.41
    Act Density 0.018%

    No Known Activations