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
     DataAccess
    -0.07
    Leo
    -0.07
    .tar
    -0.06
     pregnant
    -0.06
    .ali
    -0.06
    Архів
    -0.06
     Newfoundland
    -0.06
    		↵		↵		↵
    -0.06
    =self
    -0.06
    .RE
    -0.06
    POSITIVE LOGITS
     Narrative
    0.06
     boon
    0.06
    İŞ
    0.06
     nostra
    0.06
     بخ
    0.06
     Dummy
    0.06
    istance
    0.06
    安全
    0.06
    ittle
    0.05
    ookeeper
    0.05
    Act Density 0.021%

    No Known Activations