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

    Neuronpedia

    INDEX
    Explanations

    Liberia

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aragon
    0.54
     Arvind
    0.42
     알고
    0.41
     Shaf
    0.41
     Apna
    0.41
    }}{{
    0.40
     Alamos
    0.39
     Inorganic
    0.39
     Rafa
    0.38
     QLabel
    0.38
    POSITIVE LOGITS
     Liberia
    1.56
     Liber
    1.18
    Liber
    1.09
     Monro
    0.95
     liber
    0.87
     ليب
    0.63
     Sierra
    0.61
    Sierra
    0.61
     Ebola
    0.61
    lib
    0.60
    Act Density 0.002%

    No Known Activations