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

    Neuronpedia

    INDEX
    Explanations

    clear and define

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    缫
    0.84
    셜
    0.82
    InitStruct
    0.81
     الثانيه
    0.79
    থেষ্ট
    0.78
     Familie
    0.78
     stuffs
    0.77
     surely
    0.76
     Threatened
    0.76
     swears
    0.76
    POSITIVE LOGITS
     ràng
    0.96
     concise
    0.89
    cut
    0.88
    Cut
    0.86
     delineation
    0.83
     定义
    0.81
    定義
    0.80
    เจน
    0.79
     demarcation
    0.77
    liness
    0.76
    Act Density 0.232%

    No Known Activations