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

    Neuronpedia

    INDEX
    Explanations

    However, also, with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     firearms
    0.38
     automobiles
    0.35
     ys
    0.33
    ماية
    0.33
     depred
    0.33
     économiques
    0.32
     العامة
    0.31
    ناس
    0.31
     seguridad
    0.31
     quieras
    0.30
    POSITIVE LOGITS
    uradaki
    0.31
     уточ
    0.31
     признаки
    0.31
    ན
    0.31
    lb
    0.31
    ad
    0.30
     עם
    0.30
     изменение
    0.30
    특히
    0.30
    avec
    0.30
    Act Density 0.102%

    No Known Activations