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

    Neuronpedia

    INDEX
    Explanations

    Chinese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :{
    -0.09
    gaand
    -0.08
     omad
    -0.08
     специализирован
    -0.08
     dummy
    -0.08
     ggf
    -0.08
     vaginal
    -0.07
     möglicherweise
    -0.07
     beachten
    -0.07
     posten
    -0.07
    POSITIVE LOGITS
    梦想
    0.14
    岁
    0.11
     梦
    0.11
     whispers
    0.10
    青春
    0.10
    成长
    0.10
    激情
    0.10
     serenity
    0.10
    奋斗
    0.10
     प्रेम
    0.10
    Act Density 0.102%

    No Known Activations