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

    Neuronpedia

    INDEX
    Explanations

    authorities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -host
    -0.07
     Agreement
    -0.07
     disagreed
    -0.07
    Clock
    -0.07
    moved
    -0.07
     interviewing
    -0.07
     зрост
    -0.06
    uerdo
    -0.06
    ุมภาพ
    -0.06
     Graz
    -0.06
    POSITIVE LOGITS
     authorities
    0.31
     Authorities
    0.23
    Authorities
    0.21
     власти
    0.08
     Erd
    0.07
    [Test
    0.06
    рус
    0.06
    _VOLUME
    0.06
    (entity
    0.06
    후
    0.06
    Act Density 0.004%

    No Known Activations