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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .books
    -0.07
     RTE
    -0.06
     yp
    -0.06
    te
    -0.06
    (dest
    -0.06
     后
    -0.06
    ura
    -0.06
    Logical
    -0.06
    currentPage
    -0.06
    _INFO
    -0.06
    POSITIVE LOGITS
    лаз
    0.07
     Thankfully
    0.07
     malzem
    0.07
    ActionPerformed
    0.06
    (argument
    0.06
     subpo
    0.06
    高等
    0.06
     Açık
    0.06
    Fortunately
    0.06
    卒
    0.06
    Act Density 0.030%

    No Known Activations