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

    Neuronpedia

    INDEX
    Explanations

    abstract nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    --“
    0.52
    ป็น
    0.46
     foundational
    0.45
     जुड़ी
    0.45
    ज़ा
    0.44
     éstas
    0.43
    ඍ
    0.42
    ड़ी
    0.42
    ਸ਼
    0.42
    ඌ
    0.42
    POSITIVE LOGITS
     XNUMX
    0.82
     ​​
    0.74
     և
    0.57
     ​​​​
    0.52
    NUMX
    0.50
     ′
    0.47
     abroad
    0.46
     !!!
    0.45
     !!
    0.44
    🇧
    0.44
    Act Density 0.007%

    No Known Activations