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

    Neuronpedia

    INDEX
    Explanations

    to followed by verbs or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    রা
    0.31
    viving
    0.30
     suatu
    0.28
     SSH
    0.28
    v
    0.28
    wak
    0.28
     semaphore
    0.27
    OC
    0.26
     AB
    0.26
     man
    0.25
    POSITIVE LOGITS
    \
    0.30
    Л
    0.28
    Бе
    0.27
    Литература
    0.27
    Ги
    0.25
    기
    0.25
    ИН
    0.25
    Ι
    0.25
     코
    0.24
    HexString
    0.24
    Act Density 0.199%

    No Known Activations