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

    Neuronpedia

    INDEX
    Explanations

    device mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    臨床
    0.36
    лосо
    0.35
     масштаб
    0.35
     обслуживания
    0.35
     бюджет
    0.35
     Boeh
    0.34
    জীবী
    0.34
     probation
    0.33
    служи
    0.33
     comprim
    0.33
    POSITIVE LOGITS
    instance
    0.36
    实例
    0.36
    >{{
    0.36
    div
    0.35
     h
    0.34
    േണ്ട
    0.34
    Super
    0.33
     gsi
    0.33
     instance
    0.33
    Students
    0.33
    Act Density 0.001%

    No Known Activations