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

    Neuronpedia

    INDEX
    Explanations

    above or below average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    转换
    -0.07
    stata
    -0.07
    انا
    -0.07
    anna
    -0.07
    andre
    -0.07
     indiv
    -0.07
    厂
    -0.07
     projects
    -0.07
    бан
    -0.07
     Malawi
    -0.07
    POSITIVE LOGITS
    ordinary
    0.11
     abnormal
    0.11
     unnatural
    0.11
     ungewöhn
    0.11
     способности
    0.11
     unusually
    0.10
     unusual
    0.10
     बुद्ध
    0.10
     außergewöhn
    0.09
     ponad
    0.09
    Act Density 0.034%

    No Known Activations