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

    Neuronpedia

    INDEX
    Explanations

    government and procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nr
    -0.07
    延
    -0.07
    iband
    -0.07
    党
    -0.06
    oki
    -0.06
     Mahmoud
    -0.06
    heets
    -0.06
     مردم
    -0.06
     bureaucracy
    -0.06
    ятия
    -0.06
    POSITIVE LOGITS
     Journal
    0.07
    Người
    0.07
     smarty
    0.07
     cient
    0.06
     사용
    0.06
    Share
    0.06
     kang
    0.06
    inicio
    0.06
     brun
    0.06
    research
    0.06
    Act Density 0.343%

    No Known Activations