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

    Neuronpedia

    INDEX
    Explanations

    Roko's Basilisk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     distinctions
    0.88
     Provinc
    0.84
     Пі
    0.79
     substantiated
    0.78
     Tổng
    0.78
     CONTIN
    0.77
     Pública
    0.77
     Napole
    0.76
     País
    0.75
     Ét
    0.73
    POSITIVE LOGITS
    st
    0.89
    us
    0.84
    ts
    0.83
    ut
    0.82
    en
    0.82
    pp
    0.81
    frying
    0.81
    ul
    0.80
    mapping
    0.79
    apparent
    0.79
    Act Density 0.002%

    No Known Activations