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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     불
    -0.06
     onlar
    -0.06
     unicorn
    -0.06
    рою
    -0.06
     DBHelper
    -0.06
     �
    -0.06
    宇
    -0.06
    oltip
    -0.06
    Дж
    -0.06
    FFFFFFFF
    -0.06
    POSITIVE LOGITS
    FINAL
    0.07
     easily
    0.07
    MATCH
    0.07
    211
    0.07
    live
    0.07
    ACY
    0.07
    ifestyles
    0.07
    -working
    0.07
     Scholarship
    0.07
    (items
    0.07
    Act Density 0.002%

    No Known Activations