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

    Neuronpedia

    INDEX
    Explanations

    time periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dư
    -0.06
    _strategy
    -0.06
     propagation
    -0.06
    反应
    -0.06
    blr
    -0.06
     yielded
    -0.06
     fileName
    -0.06
    <Person
    -0.06
    ไซต
    -0.06
    ในท
    -0.06
    POSITIVE LOGITS
    .inject
    0.07
     мови
    0.07
    authenticate
    0.07
     І
    0.06
    ocha
    0.06
     electrónico
    0.06
    .Cryptography
    0.06
    běhu
    0.06
    pton
    0.06
     astronauts
    0.06
    Act Density 0.015%

    No Known Activations