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

    Neuronpedia

    INDEX
    Explanations

    f:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oretically
    1.08
    ا
    0.98
     SNPs
    0.96
    мо
    0.94
    ли
    0.90
    либо
    0.90
    から
    0.89
    ভাবে
    0.89
    льно
    0.88
    шет
    0.88
    POSITIVE LOGITS
    it
    1.20
     escrita
    1.18
    Rah
    1.07
    n
    1.07
     Página
    1.04
     gebru
    0.99
    Бе
    0.94
    ﮑ
    0.93
    ENCI
    0.92
     Klas
    0.92
    Act Density 0.673%

    No Known Activations