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

    Neuronpedia

    INDEX
    Explanations

    code definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     යා
    0.40
    opera
    0.38
     Intelig
    0.37
     Intelligence
    0.36
    izadas
    0.36
     connotations
    0.36
    velopment
    0.35
     مک
    0.35
     periód
    0.35
     excels
    0.35
    POSITIVE LOGITS
    rpart
    0.38
    罡
    0.38
    图
    0.38
    чок
    0.37
    дал
    0.37
    数
    0.37
    丘
    0.37
    সাব
    0.36
     tattooing
    0.36
    关键词
    0.36
    Act Density 0.000%

    No Known Activations