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

    Neuronpedia

    INDEX
    Explanations

    non-ascii characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bulld
    0.45
    ర
    0.42
     boilerplate
    0.42
     Nested
    0.42
     Milestone
    0.41
     supernatant
    0.41
     Charcoal
    0.41
     martyr
    0.40
     bulldozer
    0.40
     Mermaid
    0.40
    POSITIVE LOGITS
    ę
    0.61
    iki
    0.58
    ý
    0.57
    ue
    0.56
     một
    0.55
    Liên
    0.55
    س
    0.54
    Een
    0.54
    ة
    0.54
    به
    0.53
    Act Density 3.368%

    No Known Activations