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

    Neuronpedia

    INDEX
    Explanations

    papel, papaya, papas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    1.39
    ي
    1.30
    י
    1.29
    4
    1.20
    yı
    1.18
    3
    1.17
    etter
    1.09
    ه
    1.08
    upp
    1.05
    İN
    1.04
    POSITIVE LOGITS
    ing
    1.19
     de
    1.11
    ь
    1.07
    </b>
    1.04
    ны
    1.02
    p
    1.01
    n
    0.99
    </h2>
    0.96
    ска
    0.96
    <unused392>
    0.96
    Act Density 0.000%

    No Known Activations