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

    Neuronpedia

    INDEX
    Explanations

    end of period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ួរ
    0.40
    нуть
    0.38
     novel
    0.38
    block
    0.36
    each
    0.36
    blok
    0.35
     Novel
    0.35
     cet
    0.35
    lio
    0.35
    quirements
    0.35
    POSITIVE LOGITS
    OCH
    0.43
     दंपति
    0.42
    LANGUAGE
    0.41
    SEP
    0.40
    曜日
    0.39
    VENTORY
    0.39
     половины
    0.38
     ezingu
    0.38
    COMPONENT
    0.36
     दंप
    0.36
    Act Density 0.006%

    No Known Activations