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

    Neuronpedia

    INDEX
    Explanations

    theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aging
    -0.07
    feof
    -0.06
     Ars
    -0.06
    中学
    -0.06
    uat
    -0.06
     woods
    -0.06
    ibrary
    -0.06
    tica
    -0.06
    こん
    -0.06
    _sta
    -0.06
    POSITIVE LOGITS
    HttpRequest
    0.07
    把
    0.06
    ратег
    0.06
     ظرف
    0.06
    "]),
    0.06
     predominant
    0.06
    cities
    0.06
    计
    0.06
    aj
    0.06
    ู้
    0.06
    Act Density 0.001%

    No Known Activations