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

    Neuronpedia

    INDEX
    Explanations

    nav prefix and follow-on words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ova
    0.42
     .
    0.38
     প্রাণ
    0.38
    个人的
    0.38
    مو
    0.38
    地的
    0.38
    میں
    0.38
     inför
    0.37
    zon
    0.37
     introduce
    0.36
    POSITIVE LOGITS
     navigated
    0.86
     navig
    0.85
     Nav
    0.81
     navigational
    0.81
     navigating
    0.81
     navigator
    0.79
    Nav
    0.74
     navigate
    0.74
     navigation
    0.73
    Navigate
    0.73
    Act Density 0.007%

    No Known Activations