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

    Neuronpedia

    INDEX
    Explanations

    Android operating system software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    读取
    0.57
    用来
    0.49
    ור
    0.48
    כ
    0.47
    🗡
    0.47
     گھ
    0.46
    栱
    0.46
     מק
    0.44
    👓
    0.44
    闇
    0.44
    POSITIVE LOGITS
     OS
    0.52
     Software
    0.50
     Operating
    0.45
     Lite
    0.45
     Premium
    0.44
     Eco
    0.44
     ECO
    0.43
     Employee
    0.43
     Cream
    0.43
     retirement
    0.43
    Act Density 0.032%

    No Known Activations