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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h1>
    0.74
    oque
    0.74
    :
    0.70
     Paw
    0.69
    Paw
    0.66
    as
    0.66
    o
    0.65
    i
    0.64
    '
    0.62
    ession
    0.62
    POSITIVE LOGITS
    ع
    0.99
    𒂵
    0.97
    د
    0.94
     κάτι
    0.91
    ت
    0.88
     Wochschr
    0.87
    𝐽
    0.85
     valide
    0.85
     yalnız
    0.83
    𝐾
    0.83
    Act Density 0.001%

    No Known Activations