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

    Neuronpedia

    INDEX
    Explanations

    easier

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    marshall
    -0.08
     Dar
    -0.06
     redes
    -0.06
     EXIT
    -0.06
     Они
    -0.06
    甘
    -0.06
    inject
    -0.06
     epoxy
    -0.06
    serializer
    -0.06
     Canary
    -0.06
    POSITIVE LOGITS
     vyk
    0.07
     перед
    0.07
     hep
    0.07
     performance
    0.06
     nackt
    0.06
    .obs
    0.06
     Printer
    0.06
     elong
    0.06
    WE
    0.06
     вертик
    0.06
    Act Density 0.046%

    No Known Activations