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

    Neuronpedia

    INDEX
    Explanations

    12

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بوده
    -0.06
     #%
    -0.06
    к
    -0.06
    ك
    -0.06
    ific
    -0.06
     OPTIONAL
    -0.06
     inve
    -0.06
     Nack
    -0.06
     ranks
    -0.06
    III
    -0.06
    POSITIVE LOGITS
    empre
    0.07
    (rule
    0.07
     re
    0.06
    endra
    0.06
    لفة
    0.06
    Brad
    0.06
     /\
    0.06
    ,},↵
    0.06
    Interpolator
    0.06
     переп
    0.06
    Act Density 0.001%

    No Known Activations