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

    Neuronpedia

    INDEX
    Explanations

    depth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elivery
    -0.07
    лася
    -0.07
     zů
    -0.07
    emu
    -0.07
     defaultCenter
    -0.06
    .beh
    -0.06
     leven
    -0.06
    ère
    -0.06
     eoqkrvldkf
    -0.06
    ουν
    -0.06
    POSITIVE LOGITS
     初
    0.07
    ?'
    0.07
     AJ
    0.06
     RJ
    0.06
     Συ
    0.06
     complexity
    0.06
     employs
    0.06
     require
    0.06
     fz
    0.06
     Constructors
    0.06
    Act Density 0.007%

    No Known Activations