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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.77
     resourceCulture
    -0.76
     onCancelled
    -0.69
    atguigu
    -0.67
    帖最后由
    -0.63
    ThroughAttribute
    -0.62
     disponibilités
    -0.62
     للمعارف
    -0.61
     CreateTagHelper
    -0.61
    SharedCtor
    -0.60
    POSITIVE LOGITS
     Demos
    0.54
     Anſ
    0.54
     Dov
    0.54
    kaan
    0.52
    έ
    0.52
     Diſ
    0.51
     puk
    0.51
    veu
    0.51
     Eury
    0.51
     Baruch
    0.50
    Act Density 1.148%

    No Known Activations