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

    Neuronpedia

    INDEX
    Explanations

    say "iction"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deform
    -0.07
     Dry
    -0.07
     imdb
    -0.07
    gment
    -0.06
    orsche
    -0.06
     há
    -0.06
     북
    -0.06
    .LinkedList
    -0.06
     cấp
    -0.06
    HashSet
    -0.06
    POSITIVE LOGITS
    -aff
    0.06
    ﾘ
    0.06
    authenticated
    0.06
    atabase
    0.06
    ][
    0.06
    	NdrFc
    0.06
     společnosti
    0.06
     convertView
    0.06
    prisingly
    0.06
    ๒
    0.06
    Act Density 0.003%

    No Known Activations