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

    Neuronpedia

    INDEX
    Explanations

    link and path separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anthus
    0.33
    8
    0.33
    力が
    0.32
    NC
    0.31
    ு
    0.31
     расстоянии
    0.30
     embellished
    0.30
    llen
    0.30
    WA
    0.29
    LL
    0.29
    POSITIVE LOGITS
    about
    0.63
    HomePage
    0.55
    About
    0.53
    index
    0.52
    donate
    0.51
    pages
    0.50
    home
    0.50
     About
    0.49
    #!
    0.48
    ABOUT
    0.48
    Act Density 0.027%

    No Known Activations