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

    Neuronpedia

    INDEX
    Explanations

    date and time formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Modeling
    0.37
    gnu
    0.36
     INPUT
    0.36
    Educational
    0.36
    Exclusive
    0.35
    Operating
    0.35
    intos
    0.35
    Stephen
    0.35
     exclus
    0.35
     Nine
    0.34
    POSITIVE LOGITS
    月的
    0.43
    OfMonth
    0.43
     веб
    0.41
    月
    0.40
     дни
    0.39
     દિવસ
    0.37
    ਦਾ
    0.37
    писи
    0.36
    ляется
    0.36
    <0xBD>
    0.36
    Act Density 0.003%

    No Known Activations