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

    Neuronpedia

    INDEX
    Explanations

    makes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pairwise
    -0.08
     Plates
    -0.07
     أخرى
    -0.06
    tom
    -0.06
    .Replace
    -0.06
     compare
    -0.06
     appreciate
    -0.06
     Gott
    -0.06
     Path
    -0.06
     adventurers
    -0.06
    POSITIVE LOGITS
    である
    0.07
    WidgetItem
    0.07
    ＼＼
    0.07
    DD
    0.06
    anyl
    0.06
     şimdi
    0.06
    ">',↵
    0.06
     inconvenient
    0.06
     pomáh
    0.06
    ixe
    0.06
    Act Density 0.175%

    No Known Activations