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

    Neuronpedia

    INDEX
    Explanations

    roomChilddatabase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sunday
    0.22
     समाजसेवी
    0.22
    ຄວາມ
    0.22
    ಬ್ಬಳ್ಳಿ
    0.21
     सूफ़ी
    0.21
    Advertisement
    0.21
    Saturday
    0.20
    赐
    0.20
    媜
    0.20
     усили
    0.20
    POSITIVE LOGITS
     avulla
    0.26
     wit
    0.24
     seng
    0.24
     using
    0.22
     ras
    0.20
     asing
    0.20
     orbit
    0.20
     gebruiken
    0.20
     /
    0.20
     zone
    0.20
    Act Density 0.181%

    No Known Activations