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

    Neuronpedia

    INDEX
    Explanations

    Quadr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Œ
    -0.09
     neug
    -0.08
    Il
    -0.08
    Nie
    -0.08
     leaking
    -0.08
     curiosity
    -0.08
     speculation
    -0.07
     urg
    -0.07
    Nec
    -0.07
    oard
    -0.07
    POSITIVE LOGITS
     최고의
    0.10
     മികച്ച
    0.09
    .tests
    0.09
     judged
    0.09
     finalist
    0.09
     평가
    0.09
     bewertet
    0.09
    排名
    0.09
     рейтинг
    0.09
     interviewing
    0.08
    Act Density 0.031%

    No Known Activations