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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ають
    -0.08
    ological
    -0.08
    masına
    -0.07
    irical
    -0.07
    mary
    -0.07
     блю
    -0.07
    олога
    -0.07
     خیال
    -0.07
    anghai
    -0.07
    psilon
    -0.07
    POSITIVE LOGITS
     employers
    0.10
    recommended
    0.09
     employer
    0.09
     personal
    0.08
     recommended
    0.08
    أفضل
    0.08
    Etat
    0.08
     persönliche
    0.08
    Recommended
    0.08
    Créer
    0.08
    Act Density 0.001%

    No Known Activations