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

    Neuronpedia

    INDEX
    Explanations

    id and name identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     list
    0.45
     EVs
    0.42
     scores
    0.41
     values
    0.41
     boys
    0.41
     baseball
    0.40
     prices
    0.39
    ሮች
    0.39
     retail
    0.38
     suggestions
    0.38
    POSITIVE LOGITS
    ເຄື່ອງ
    0.46
    案件
    0.45
     издели
    0.44
     мероприя
    0.44
     spineItem
    0.44
     tématu
    0.43
     Projeto
    0.43
     publicación
    0.43
     கடை
    0.43
    mxCell
    0.43
    Act Density 0.012%

    No Known Activations