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

    Neuronpedia

    INDEX
    Explanations

    mind's eye

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.17
    ।
    0.17
    пас
    0.16
    <unused963>
    0.16
     تعین
    0.16
     modeled
    0.15
     fea
    0.15
    ↵
    0.15
    scp
    0.15
    дио
    0.15
    POSITIVE LOGITS
     esimerk
    0.18
     sobot
    0.18
     başladı
    0.17
    ༔
    0.17
     ž
    0.17
     kü
    0.17
     कक्कड़
    0.17
     jumpsuit
    0.17
     jei
    0.17
     ieri
    0.17
    Act Density 0.000%

    No Known Activations