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

    Neuronpedia

    INDEX
    Explanations

    text discussing politics, especially concerning the working class

    oai_token-act-pair · gemini-2.0-flash

    Politics and working class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    려
    -0.46
     технологий
    -0.44
     Weise
    -0.43
     otro
    -0.41
     îng
    -0.40
     vaga
    -0.40
     télécommande
    -0.40
    zon
    -0.40
     разобра
    -0.40
    unikasi
    -0.39
    POSITIVE LOGITS
    Personensuche
    0.85
    featureID
    0.85
    TagMode
    0.76
     Majefty
    0.71
    NameInMap
    0.71
     ་་
    0.70
    ſelf
    0.68
    SharedDtor
    0.67
    InjectAttribute
    0.67
     المعيارى
    0.67
    Act Density 1.513%

    No Known Activations