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

    Neuronpedia

    INDEX
    Explanations

    Random text/noise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fashionable
    -0.08
    胆
    -0.07
     quir
    -0.07
    gpu
    -0.06
     beau
    -0.06
    자의
    -0.06
     frequently
    -0.06
    Front
    -0.06
     Rout
    -0.06
    inventory
    -0.06
    POSITIVE LOGITS
    .AD
    0.07
    ircles
    0.07
     Monad
    0.06
     Checker
    0.06
    (fh
    0.06
     unify
    0.06
    olo
    0.06
    :"
    0.06
     harmony
    0.06
    .Nil
    0.06
    Act Density 0.224%

    No Known Activations