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

    Neuronpedia

    INDEX
    Explanations

    attacks against journalists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amort
    -0.09
     QString
    -0.08
     decoded
    -0.08
     vorbei
    -0.08
    formatted
    -0.08
     第二
    -0.08
     दूरी
    -0.08
     优
    -0.08
     formatted
    -0.08
     Decode
    -0.08
    POSITIVE LOGITS
     persecution
    0.10
     martyr
    0.09
     intimidation
    0.09
     protects
    0.09
     repris
    0.09
     retaliation
    0.09
    遭
    0.09
     vandal
    0.09
     crackdown
    0.09
     journalist
    0.09
    Act Density 0.103%

    No Known Activations