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

    Neuronpedia

    INDEX
    Explanations

    wanted to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    麻木
    -0.07
    ้อน
    -0.07
    稳固
    -0.07
    这几天
    -0.06
    .exam
    -0.06
    柒
    -0.06
     Reggie
    -0.06
    反思
    -0.06
    警惕
    -0.06
    振り
    -0.06
    POSITIVE LOGITS
    .kernel
    0.08
     pioneers
    0.07
    .pres
    0.07
    Enterprise
    0.07
    وس
    0.07
     carts
    0.07
    >c
    0.07
    �s
    0.07
     tren
    0.07
    rowse
    0.07
    Act Density 0.027%

    No Known Activations