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

    Neuronpedia

    INDEX
    Explanations

    God's existence and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ab
    1.00
     géographique
    0.96
     auxqu
    0.95
    il
    0.92
    ség
    0.92
    ALO
    0.89
    оти
    0.89
     أوروب
    0.89
     gewährleisten
    0.88
    浲
    0.88
    POSITIVE LOGITS
     and
    1.52
    น
    1.37
     God
    1.19
    _
    1.16
    н
    1.16
    '
    1.09
     on
    1.06
    ↵
    1.05
    я
    1.04
    ีย
    1.03
    Act Density 0.039%

    No Known Activations