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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -open
    -0.07
    egin
    -0.06
    不可
    -0.06
     Slot
    -0.06
     Vapor
    -0.06
    रत
    -0.06
    итив
    -0.06
    /process
    -0.06
    _CLUSTER
    -0.06
     STORE
    -0.06
    POSITIVE LOGITS
     devant
    0.06
     куль
    0.06
     císa
    0.06
     Ре
    0.06
     Xu
    0.06
    elix
    0.06
     rencontrer
    0.06
     serene
    0.06
     어�
    0.06
    Mais
    0.06
    Act Density 0.011%

    No Known Activations