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

    Neuronpedia

    INDEX
    Explanations

    请

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UCH
    -0.07
     Tay
    -0.07
    維
    -0.07
    啥
    -0.07
    abra
    -0.07
    Michael
    -0.07
    闿
    -0.06
     입장
    -0.06
    Watch
    -0.06
    Tax
    -0.06
    POSITIVE LOGITS
    (RE
    0.07
    ٫
    0.07
    (percent
    0.07
     inspected
    0.07
     ^(
    0.07
    وسائل
    0.07
    /features
    0.07
    进程中
    0.07
    (fake
    0.06
    '])[
    0.06
    Act Density 0.004%

    No Known Activations