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

    Neuronpedia

    INDEX
    Explanations

    column names in tables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ..--
    0.59
    জনের
    0.57
    ਂ
    0.55
    Regards
    0.54
    Assert
    0.54
    ="#">
    0.53
    앙
    0.53
     Verwendung
    0.53
    ציה
    0.53
    "/
    0.52
    POSITIVE LOGITS
    вання
    0.63
    ﺐ
    0.63
     earners
    0.62
    ان
    0.61
     Verhältnis
    0.59
     dout
    0.58
    𝖺
    0.58
    তান্ত্রিক
    0.57
     stoves
    0.57
    ä
    0.56
    Act Density 0.033%

    No Known Activations