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

    Neuronpedia

    INDEX
    Explanations

    q

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hind
    -0.08
    ڶ
    -0.07
     bach
    -0.07
    thew
    -0.06
    .ticket
    -0.06
    祖
    -0.06
    dbContext
    -0.06
    тал
    -0.06
    eci
    -0.06
    tems
    -0.06
    POSITIVE LOGITS
     cheapest
    0.07
    越大
    0.07
     어렵
    0.07
     available
    0.07
     searching
    0.07
    dataset
    0.07
    总监
    0.07
     rápida
    0.07
    amento
    0.07
     acknowledges
    0.07
    Act Density 0.000%

    No Known Activations