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

    Neuronpedia

    INDEX
    Explanations

    framework for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sever
    0.47
    範圍
    0.43
    奋
    0.40
    </h6>
    0.40
    项目中
    0.40
    </span>
    0.39
     video
    0.39
    范围
    0.39
    course
    0.39
     furtherance
    0.39
    POSITIVE LOGITS
    bedingungen
    0.61
    ک
    0.52
     Framework
    0.50
     kerja
    0.49
     çerçe
    0.49
     Kerja
    0.47
    Framework
    0.46
     frameworks
    0.45
    조건
    0.43
    応答
    0.43
    Act Density 0.011%

    No Known Activations