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

    Neuronpedia

    INDEX
    Explanations

    bert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _si
    -0.07
     nylon
    -0.07
     Roots
    -0.06
     Sandbox
    -0.06
     venom
    -0.06
     rethink
    -0.06
     rushed
    -0.06
     enclosure
    -0.06
     bringing
    -0.06
     واح
    -0.06
    POSITIVE LOGITS
    ert
    0.09
    ERT
    0.08
     Herbert
    0.07
    特
    0.07
    bert
    0.07
    트
    0.07
    UART
    0.07
     UART
    0.07
    ért
    0.07
    άρ
    0.07
    Act Density 0.024%

    No Known Activations