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

    Neuronpedia

    INDEX
    Explanations

    years of experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ты
    0.88
     คำ
    0.86
     bangsa
    0.85
     TAD
    0.83
    Па
    0.83
    єю
    0.82
     bood
    0.82
     xưa
    0.81
     egli
    0.81
    জী
    0.81
    POSITIVE LOGITS
    h
    0.97
    дә
    0.91
     بالأ
    0.84
    ίκη
    0.84
    ا
    0.81
    agnetic
    0.80
    вшийся
    0.80
    یف
    0.80
    ÉRI
    0.79
    вшиеся
    0.78
    Act Density 0.027%

    No Known Activations