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

    Neuronpedia

    INDEX
    Explanations

    Adverbs ending in "ly"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    düğü
    -0.06
    reesome
    -0.06
    Thai
    -0.06
     Bad
    -0.06
     shaky
    -0.06
     protože
    -0.06
     благодаря
    -0.06
     Cri
    -0.06
    øy
    -0.06
    (Photo
    -0.05
    POSITIVE LOGITS
     Ferdinand
    0.07
    Clearly
    0.07
     Benton
    0.07
     Clearly
    0.07
    IBC
    0.07
    Initially
    0.06
    =>"
    0.06
    急
    0.06
     aesthetics
    0.06
     pParent
    0.06
    Act Density 0.071%

    No Known Activations