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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /pkg
    -0.08
    ()%
    -0.07
     start
    -0.07
     接
    -0.07
    再
    -0.07
    krit
    -0.07
    riting
    -0.07
     wrote
    -0.07
    "):↵
    -0.06
     meaningful
    -0.06
    POSITIVE LOGITS
     činnost
    0.07
    .setIcon
    0.07
    observeOn
    0.07
     protector
    0.06
    .JMenuItem
    0.06
     πρώτη
    0.06
     oportun
    0.06
    ność
    0.06
    Chat
    0.06
    (clicked
    0.06
    Act Density 0.025%

    No Known Activations