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

    Neuronpedia

    INDEX
    Explanations

    create react app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proxy
    0.77
     Proxy
    0.77
     escena
    0.70
    metry
    0.69
     Szen
    0.69
    ossz
    0.68
     année
    0.67
    عم
    0.66
     hem
    0.66
    üle
    0.65
    POSITIVE LOGITS
    begin
    0.80
    BEGIN
    0.74
     commence
    0.72
    ख्ती
    0.71
    Startup
    0.70
     seo
    0.69
     Woot
    0.69
    discipline
    0.68
     Agust
    0.68
     gatos
    0.67
    Act Density 0.002%

    No Known Activations