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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    book
    -0.08
     circular
    -0.07
     Carl
    -0.07
     Johnson
    -0.06
    Book
    -0.06
     게시판
    -0.06
    $j
    -0.06
    Bulletin
    -0.06
    sigma
    -0.06
     fichier
    -0.06
    POSITIVE LOGITS
    âte
    0.07
     suede
    0.07
    ΟΡ
    0.07
     ):
    0.07
     xúc
    0.07
    .Completed
    0.07
    .RE
    0.06
     DWC
    0.06
     Geç
    0.06
    .connect
    0.06
    Act Density 0.014%

    No Known Activations