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

    Neuronpedia

    INDEX
    Explanations

    string literal or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    稷
    0.70
    aptop
    0.69
     easel
    0.69
     Xie
    0.67
     मंडळा
    0.66
     Institute
    0.65
     institutional
    0.65
     Parkinson
    0.65
     коммер
    0.65
     Jarvis
    0.64
    POSITIVE LOGITS
     string
    5.13
    string
    4.86
     strings
    4.86
    字符串
    4.60
    String
    4.60
     String
    4.59
     Strings
    4.38
    strings
    4.37
    文字列
    4.10
    Strings
    4.10
    Act Density 1.215%

    No Known Activations