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

    Neuronpedia

    INDEX
    Explanations

    Armenian kingdoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     análise
    1.74
     réalisée
    1.63
     considérée
    1.61
    Zé
    1.58
    kör
    1.55
     actuel
    1.52
    пература
    1.52
     agréable
    1.50
     informatique
    1.50
    kina
    1.48
    POSITIVE LOGITS
    ק
    2.08
    ת
    1.94
    ed
    1.82
     (
    1.81
    ات
    1.80
    י
    1.80
    s
    1.73
    ных
    1.70
    0
    1.65
    ↵
    1.64
    Act Density 0.001%

    No Known Activations