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

    Neuronpedia

    INDEX
    Explanations

    specific words within phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ህ
    0.45
    Congress
    0.44
    iology
    0.44
     tobacco
    0.43
    ਲੇ
    0.42
    icine
    0.42
     poison
    0.41
     प्रच
    0.41
    i
    0.41
     Congress
    0.41
    POSITIVE LOGITS
     omdat
    0.45
     உள
    0.45
     pytanie
    0.44
     cerca
    0.43
     kteří
    0.43
     grupy
    0.43
     memanfaatkan
    0.43
     setSelected
    0.43
     cuya
    0.42
     stronę
    0.42
    Act Density 0.003%

    No Known Activations