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

    Neuronpedia

    INDEX
    Explanations

    questions starting with what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     útiles
    0.68
    <unused2013>
    0.64
     यात्रियों
    0.63
     படங்கள்
    0.62
    ículas
    0.61
     máquinas
    0.61
    pias
    0.60
     utilises
    0.60
     عناصر
    0.59
     revistas
    0.59
    POSITIVE LOGITS
    o
    0.77
    ↵
    0.74
    s
    0.71
    y
    0.68
    ↵↵
    0.66
    k
    0.66
    f
    0.63
    w
    0.60
     time
    0.58
    at
    0.57
    Act Density 0.155%

    No Known Activations