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

    Neuronpedia

    INDEX
    Explanations

    introduction and hook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assayed
    0.45
     HONOR
    0.41
     tutorials
    0.39
    detailID
    0.39
     workable
    0.38
     advice
    0.38
    แหล่ง
    0.37
     backend
    0.37
     aftermarket
    0.37
    配置文件
    0.36
    POSITIVE LOGITS
     introducir
    0.76
    Introduce
    0.73
     introduction
    0.71
     Introduce
    0.70
     introducing
    0.70
     Introdu
    0.70
     introduces
    0.69
    introdu
    0.68
     introduce
    0.68
     Introduction
    0.68
    Act Density 0.016%

    No Known Activations