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

    Neuronpedia

    INDEX
    Explanations

    scientific acronyms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pairwise
    -0.07
     digital
    -0.07
    ай
    -0.07
     Dirt
    -0.07
    	login
    -0.07
     ferry
    -0.06
    -pic
    -0.06
    ван
    -0.06
     lúc
    -0.06
     reserve
    -0.06
    POSITIVE LOGITS
    ΩΤ
    0.06
    inburgh
    0.06
    723
    0.06
    raith
    0.06
     शक
    0.06
     손
    0.06
    ,NULL
    0.06
    润
    0.06
     goog
    0.06
    การเล
    0.06
    Act Density 0.030%

    No Known Activations