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

    Neuronpedia

    INDEX
    Explanations

    Christ and Christian terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éraire
    0.42
    刑事
    0.41
     Jalis
    0.39
    éticas
    0.37
    เท่า
    0.37
     Fats
    0.37
     disseminated
    0.36
    trif
    0.36
     Calculations
    0.36
     שת
    0.36
    POSITIVE LOGITS
    ians
    0.75
    ophers
    0.74
    iaan
    0.71
    opher
    0.71
    offel
    0.70
    ian
    0.67
    IAN
    0.63
    ianos
    0.62
     ian
    0.62
    iano
    0.59
    Act Density 0.002%

    No Known Activations