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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stunned
    -0.07
     onStart
    -0.07
    fasta
    -0.07
    منتدى
    -0.07
     rallied
    -0.07
     radioButton
    -0.07
    -0.06
    Congratulations
    -0.06
     Владимир
    -0.06
    !!↵
    -0.06
    POSITIVE LOGITS
     Ruiz
    0.07
    璃
    0.07
    מח
    0.07
     UserDao
    0.07
    終於
    0.07
    万家
    0.06
     Rs
    0.06
     śl
    0.06
     cáo
    0.06
    锥
    0.06
    Act Density 0.004%

    No Known Activations