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

    Neuronpedia

    INDEX
    Explanations

    population figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Länder
    0.46
    countries
    0.43
    COUNTRY
    0.41
    მწიფ
    0.40
    AGUE
    0.39
    germ
    0.38
    ፈላ
    0.38
    चीनी
    0.38
    स्पर्
    0.38
     ممالک
    0.37
    POSITIVE LOGITS
     was
    0.44
     był
    0.44
     reported
    0.44
     latest
    0.44
     było
    0.42
     terbaru
    0.41
     était
    0.40
     byl
    0.39
     reportedly
    0.39
     bylo
    0.39
    Act Density 0.022%

    No Known Activations