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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aç
    -0.08
     hydrogen
    -0.07
     Optional
    -0.06
    H
    -0.06
     yapmak
    -0.06
     prostřednictvím
    -0.06
    fone
    -0.06
    odate
    -0.06
    odesk
    -0.06
    manın
    -0.06
    POSITIVE LOGITS
     heav
    0.07
    ุตบอล
    0.07
     Auction
    0.06
    ependency
    0.06
    ecd
    0.06
    cherche
    0.06
    separator
    0.06
    駅徒歩
    0.06
    حدة
    0.06
    .GET
    0.06
    Act Density 0.080%

    No Known Activations