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

    Neuronpedia

    INDEX
    Explanations

    did

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grief
    -0.07
     testing
    -0.07
     Yep
    -0.07
     seb
    -0.07
     fw
    -0.06
    cee
    -0.06
     bathing
    -0.06
     имп
    -0.06
    iga
    -0.06
     مدت
    -0.06
    POSITIVE LOGITS
    _StaticFields
    0.07
    ریق
    0.07
    abase
    0.07
    _PIPE
    0.06
     Isabel
    0.06
    090
    0.06
     nettsteder
    0.06
    선
    0.06
    staw
    0.06
    ische
    0.06
    Act Density 0.003%

    No Known Activations