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

    Neuronpedia

    INDEX
    Explanations

    templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transitory
    0.44
    Commissioner
    0.41
     आयुक्त
    0.41
     commissioner
    0.39
    roscopic
    0.38
     commissioners
    0.37
    countplot
    0.36
    돗
    0.36
     Commissioner
    0.36
     აღმასრულებელი
    0.35
    POSITIVE LOGITS
     template
    4.50
     templates
    4.22
    template
    4.03
    模板
    3.95
     Template
    3.94
    Template
    3.88
    テンプレート
    3.88
     Templates
    3.81
    Templates
    3.56
     шабло
    3.56
    Act Density 0.115%

    No Known Activations