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

    Neuronpedia

    INDEX
    Explanations

    URLs with category, blog, reviews, or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     only
    0.38
     in
    0.35
     suitable
    0.35
     against
    0.33
    '
    0.33
     to
    0.32
     on
    0.32
     an
    0.32
     having
    0.32
    ',
    0.31
    POSITIVE LOGITS
    accueil
    0.39
    index
    0.37
    /"+
    0.36
    उन
    0.36
    topics
    0.35
    HomePage
    0.35
    ublik
    0.35
    onglet
    0.35
    explore
    0.35
    articolo
    0.35
    Act Density 0.014%

    No Known Activations