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

    Neuronpedia

    INDEX
    Explanations

    division by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Released
    0.41
     తో
    0.41
     Workshops
    0.40
    πέ
    0.39
    <unused338>
    0.39
     জ
    0.39
     নং
    0.39
     Library
    0.39
     Purification
    0.38
     Proverbs
    0.38
    POSITIVE LOGITS
     immediacy
    0.45
    лып
    0.44
     antig
    0.43
     entender
    0.40
     preju
    0.40
     airflow
    0.39
     an
    0.38
    systems
    0.38
     konserv
    0.38
     headwinds
    0.38
    Act Density 0.002%

    No Known Activations