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

    Neuronpedia

    INDEX
    Explanations

    HTML templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pestic
    0.44
     superhuman
    0.43
     scholarship
    0.42
    рафон
    0.42
     تیل
    0.42
    athlet
    0.41
     stimulant
    0.41
    дных
    0.41
    selValue
    0.41
     causation
    0.41
    POSITIVE LOGITS
     template
    0.97
     templates
    0.96
     Templates
    0.93
    template
    0.92
    Template
    0.90
     Template
    0.88
    模板
    0.85
    templates
    0.84
    Templates
    0.84
     шабло
    0.80
    Act Density 0.057%

    No Known Activations