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

    Neuronpedia

    INDEX
    Explanations

    born phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ع
    1.46
    ۔
    1.20
    ку
    1.20
    ה
    1.16
    ي
    1.16
    ای
    1.14
    述べ
    1.09
     infringe
    1.05
    З
    1.05
    علي
    1.05
    POSITIVE LOGITS
    ↵
    1.30
     lahir
    1.23
     Born
    1.16
     born
    1.12
     Birth
    1.05
     birth
    1.01
    _
    0.97
    born
    0.96
     Health
    0.88
     Bio
    0.88
    Act Density 0.006%

    No Known Activations