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

    Neuronpedia

    INDEX
    Explanations

    The Wire

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("?
    -0.06
     nackte
    -0.06
     Lace
    -0.06
    éis
    -0.06
    nearest
    -0.06
    최고
    -0.06
    _solve
    -0.06
     Labels
    -0.06
     vídeo
    -0.06
     ид
    -0.06
    POSITIVE LOGITS
     RTS
    0.07
    ád
    0.07
     soci
    0.07
     redistrib
    0.07
    369
    0.06
     SignUp
    0.06
     strategic
    0.06
     problems
    0.06
     ADMIN
    0.06
    ulario
    0.06
    Act Density 0.061%

    No Known Activations