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

    Neuronpedia

    INDEX
    Explanations

    Gibberish/Nonsense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     read
    -0.07
     remedy
    -0.07
     cowboy
    -0.06
    ycop
    -0.06
    upported
    -0.06
     ovliv
    -0.06
     KUR
    -0.06
    .csv
    -0.06
     方
    -0.06
     Ordered
    -0.06
    POSITIVE LOGITS
     gerekiyor
    0.07
    iktig
    0.07
    hots
    0.06
     CONST
    0.06
    unist
    0.06
    subscriptions
    0.06
    	Me
    0.06
     där
    0.06
    deo
    0.06
     vole
    0.06
    Act Density 0.116%

    No Known Activations