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

    Neuronpedia

    INDEX
    Explanations

    national community company levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    细节
    0.27
     분야
    0.25
     Amount
    0.25
     세상
    0.25
     संसार
    0.25
    étant
    0.24
    作为
    0.24
     Universe
    0.24
     hefty
    0.24
    广大
    0.24
    POSITIVE LOGITS
    wide
    0.62
    WIDE
    0.52
    व्यापी
    0.49
    level
    0.39
    Wide
    0.38
     পর্যায়ে
    0.37
    weiten
    0.37
     wide
    0.37
     affairs
    0.37
     পর্যায়ে
    0.36
    Act Density 0.180%

    No Known Activations