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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "Say"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ขัน
    0.40
    aglio
    0.39
    櫂
    0.39
    对应的
    0.38
    ابد
    0.37
     Alli
    0.37
    تقد
    0.37
    रिट
    0.37
    igion
    0.36
    ченных
    0.36
    POSITIVE LOGITS
     Say
    0.46
    ings
    0.45
     ura
    0.40
    من
    0.39
     नमस्कार
    0.38
     sayang
    0.38
    pol
    0.37
    Say
    0.37
    దవ
    0.37
    AnimationFrame
    0.37
    Act Density 0.002%

    No Known Activations