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

    Neuronpedia

    INDEX
    Explanations

    time/narrative snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.52
    Jews
    -0.49
     judiciaire
    -0.48
     Jews
    -0.48
     Erişim
    -0.47
    oil
    -0.46
    springframework
    -0.46
     AppBundle
    -0.45
    PEOPLE
    -0.45
    
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.77
     I
    0.68
    تقاوى
    0.66
    romptu
    0.65
    webElementXpaths
    0.63
     المعيارى
    0.62
     вікі
    0.55
    Geplaatst
    0.55
     незавершена
    0.55
    EndProject
    0.55
    Act Density 0.002%

    No Known Activations