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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lovely
    -0.08
    busters
    -0.08
     slots
    -0.08
    -0.07
     Fragment
    -0.07
     Amherst
    -0.07
    ந்த
    -0.07
     amput
    -0.07
     aanzien
    -0.07
     اكت
    -0.07
    POSITIVE LOGITS
     cá
    0.09
    Herm
    0.08
    ’er
    0.08
     ✅
    0.07
    alias
    0.07
     
    0.07
    뿐
    0.07
    •
    0.07
    โด
    0.07
    ·
    0.07
    Act Density 0.027%
    No Known Activations