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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺎ
    0.82
    ownic
    0.80
    ا
    0.78
    uating
    0.76
    0.76
    n
    0.76
    owników
    0.75
     актриса
    0.75
    a
    0.75
    ана
    0.73
    POSITIVE LOGITS
    ’
    0.97
    ↵
    0.94
    '
    0.80
     berkata
    0.71
    ΄
    0.67
    說
    0.66
    Funeral
    0.66
    几
    0.64
     رحمه
    0.64
    Illus
    0.63
    Act Density 0.111%

    No Known Activations