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

    Neuronpedia

    INDEX
    Explanations

    Checksums and hashing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     معالجة
    -0.08
     Hunger
    -0.08
    unched
    -0.08
     recurrent
    -0.07
    _pointer
    -0.07
    бы
    -0.07
    Constants
    -0.07
     ধার
    -0.07
    -prem
    -0.07
    serrat
    -0.07
    POSITIVE LOGITS
     élevée
    0.08
     eclipse
    0.08
     canyon
    0.07
     profiles
    0.07
     kett
    0.07
     profils
    0.07
     insensitive
    0.07
     file
    0.07
    eee
    0.07
     eject
    0.07
    Act Density 0.003%

    No Known Activations