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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bed
    -0.08
     yanlış
    -0.07
    екар
    -0.07
     mosques
    -0.06
    파트
    -0.06
     спрос
    -0.06
    counter
    -0.06
     ترتیب
    -0.06
    .Prop
    -0.06
     '/
    -0.06
    POSITIVE LOGITS
     jobId
    0.06
    ่
    0.06
    �
    0.06
     getters
    0.06
    (cuda
    0.06
    ังน
    0.06
    sono
    0.06
    (Db
    0.06
     кис
    0.06
     cursed
    0.06
    Act Density 0.048%

    No Known Activations