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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiprocessing
    -0.07
     Ni
    -0.07
    Road
    -0.07
     bulbs
    -0.06
    จำหน
    -0.06
     possessions
    -0.06
     gerekli
    -0.06
     tienes
    -0.06
    عر
    -0.06
     Rangers
    -0.06
    POSITIVE LOGITS
     quantify
    0.07
     만족
    0.06
    كتور
    0.06
     підт
    0.06
     */
↵
↵
↵
    0.06
    instagram
    0.06
    á
    0.06
    副
    0.06
     إليه
    0.06
    09
    0.06
    Act Density 0.039%

    No Known Activations