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

    Neuronpedia

    INDEX
    Explanations

    "2023/2024"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    两
    0.81
    0.81
    兩
    0.80
    兩
    0.80
     ૧
    0.80
     ۲۰۱
    0.77
     ২০১৭
    0.76
     ၁
    0.76
    0.76
    ToJava
    0.75
    POSITIVE LOGITS
    🫡
    0.74
    অধ
    0.72
    supabase
    0.72
    🫢
    0.69
    ২৪
    0.68
     streamer
    0.64
    🫶
    0.64
     ча
    0.64
    🫰
    0.63
    ܚ
    0.63
    Act Density 0.058%

    No Known Activations