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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cộng
    -0.07
    column
    -0.07
    Token
    -0.07
     foundations
    -0.07
     true
    -0.07
    961
    -0.07
     ance
    -0.07
     experts
    -0.07
    otechnology
    -0.06
     officials
    -0.06
    POSITIVE LOGITS
     مناطق
    0.06
    osite
    0.06
     lesbienne
    0.06
    sealed
    0.06
    ента
    0.06
    翻
    0.06
     ребенка
    0.06
    ucked
    0.05
    ज़
    0.05
     conced
    0.05
    Act Density 0.064%

    No Known Activations