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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kỳ
    -0.08
     pottery
    -0.08
     aldığı
    -0.08
     ör
    -0.07
     actualizar
    -0.07
    _within
    -0.07
     Diary
    -0.07
     svn
    -0.07
     précéd
    -0.07
    (clazz
    -0.07
    POSITIVE LOGITS
     definition
    0.07
    .Cloud
    0.07
     objective
    0.06
    奈
    0.06
     answering
    0.06
     bosses
    0.06
    usually
    0.06
    高端
    0.06
    娘家
    0.06
    盈利
    0.06
    Act Density 0.015%

    No Known Activations