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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ازات
    -0.07
    _SELECTED
    -0.07
    意味
    -0.06
    veled
    -0.06
    storms
    -0.06
    Directive
    -0.06
    _SERIAL
    -0.06
    мест
    -0.06
    AdminController
    -0.06
     等
    -0.06
    POSITIVE LOGITS
     山
    0.06
     слишком
    0.06
     drinkers
    0.06
    ۱۹۹
    0.06
    ğit
    0.06
     ücret
    0.06
     dép
    0.06
     hra
    0.06
     qued
    0.06
     nour
    0.06
    Act Density 0.073%

    No Known Activations