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

    Neuronpedia

    INDEX
    Explanations

    mathematical operator +

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (.
    0.43
     ৭৫
    0.40
     आजकल
    0.40
     Ru
    0.39
     ru
    0.39
    =.
    0.38
    cation
    0.38
     hagy
    0.37
     teg
    0.37
     percentile
    0.36
    POSITIVE LOGITS
    өт
    0.43
    }^{+}+
    0.38
    inflate
    0.38
    LayoutInflater
    0.37
     inflationary
    0.37
     வாக்க
    0.37
    сера
    0.37
    ाइब
    0.37
     Inflation
    0.36
    Бахар
    0.36
    Act Density 0.006%

    No Known Activations