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

    Neuronpedia

    INDEX
    Explanations

    laws in different countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     connecting
    0.44
     brillo
    0.44
     everyone
    0.42
    everyone
    0.40
     capacitor
    0.39
     quickly
    0.38
    䒽
    0.38
     connectivity
    0.38
     Yank
    0.37
     capacitors
    0.37
    POSITIVE LOGITS
     countries
    1.30
     países
    1.23
     Sweden
    1.20
    Countries
    1.19
    countries
    1.17
     Germany
    1.16
     Countries
    1.16
     देशों
    1.15
    Sweden
    1.13
     странах
    1.12
    Act Density 0.022%

    No Known Activations