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

    Neuronpedia

    INDEX
    Explanations

    angular frequency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.03
    ا
    1.02
    ت
    0.93
    '
    0.91
     impairments
    0.85
    و
    0.83
    ו
    0.83
    П
    0.81
     зависи
    0.81
    การ
    0.77
    POSITIVE LOGITS
    ра
    0.89
     by
    0.79
    리
    0.78
     Kanal
    0.77
     Tân
    0.77
     heut
    0.77
     Tentang
    0.76
    ру
    0.75
    SE
    0.74
     Genève
    0.74
    Act Density 0.002%

    No Known Activations