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

    Neuronpedia

    INDEX
    Explanations

    neural language models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Amish
    0.65
     মহানগর
    0.64
    mbito
    0.63
    ຫາ
    0.63
     oportun
    0.62
    ధ
    0.62
    maxage
    0.62
    ensington
    0.62
     bunting
    0.61
    oflavin
    0.61
    POSITIVE LOGITS
     neural
    2.22
     models
    2.22
     Neural
    2.07
     Models
    2.03
     model
    2.02
    Neural
    1.94
    模型
    1.93
     모델
    1.91
     modelos
    1.88
    模型的
    1.83
    Act Density 2.363%

    No Known Activations