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

    Neuronpedia

    INDEX
    Explanations

    öz, oz, göz, Öz, Oz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뚝
    0.38
    orough
    0.38
    䏍
    0.38
     boolean
    0.36
     Edge
    0.36
     universitaire
    0.36
     cuest
    0.36
    internalType
    0.36
    য়োগ
    0.36
     套
    0.36
    POSITIVE LOGITS
    kay
    0.45
    ell
    0.44
    lem
    0.43
    ellis
    0.43
    ellig
    0.42
    ellikle
    0.42
    lemm
    0.41
    guan
    0.41
    elle
    0.40
    de
    0.40
    Act Density 0.003%

    No Known Activations