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

    Neuronpedia

    INDEX
    Explanations

    reign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ({
    -0.07
     (${
    -0.07
    -shirt
    -0.07
     hurdle
    -0.07
    (ident
    -0.07
     kel
    -0.06
     корпус
    -0.06
    getProperty
    -0.06
    をつ
    -0.06
     tackled
    -0.06
    POSITIVE LOGITS
     Reign
    0.18
     reign
    0.14
     reigning
    0.12
     readme
    0.07
    ↵↵    ↵
    0.07
    Leading
    0.07
    ign
    0.07
    .readInt
    0.07
     planning
    0.07
     regain
    0.07
    Act Density 0.003%

    No Known Activations