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

    Neuronpedia

    INDEX
    Explanations

    some

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     succès
    -0.07
    .pth
    -0.07
    /dist
    -0.07
    combat
    -0.07
     Lower
    -0.06
     giúp
    -0.06
     علي
    -0.06
     мног
    -0.06
    مس
    -0.06
    querySelector
    -0.06
    POSITIVE LOGITS
     Ke
    0.07
    ?;↵
    0.06
    ُه
    0.06
     dame
    0.06
     motivational
    0.06
    Released
    0.06
    	yy
    0.06
     имеют
    0.06
    -animate
    0.06
    dam
    0.06
    Act Density 0.055%

    No Known Activations