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

    Neuronpedia

    INDEX
    Explanations

    ple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     расс
    -0.08
    𬭤
    -0.08
    تسويق
    -0.07
    bus
    -0.07
    Ленин
    -0.07
    聊
    -0.07
    Buzz
    -0.07
    船只
    -0.06
     detalles
    -0.06
    )init
    -0.06
    POSITIVE LOGITS
     applicable
    0.07
     compliant
    0.07
    いけ
    0.07
     relates
    0.07
     programmer
    0.07
    implicit
    0.07
     sits
    0.07
    -HT
    0.07
     gardening
    0.06
    _overlay
    0.06
    Act Density 0.004%

    No Known Activations