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

    Neuronpedia

    INDEX
    Explanations

    code comments in ruby

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     featuring
    0.40
    ")),
    0.40
     👋
    0.39
     Pá
    0.39
    QueryParams
    0.39
    "),
    0.38
     –
    0.38
     wearables
    0.37
    <0xC2>
    0.37
    另一方面
    0.37
    POSITIVE LOGITS
    西安
    0.42
    南京
    0.42
    轲
    0.42
     কলিকাতা
    0.41
    鲞
    0.41
    Pyro
    0.40
    鈮
    0.40
    蟶
    0.40
    RadioButton
    0.39
    ﻥ
    0.39
    Act Density 0.001%

    No Known Activations