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

    Neuronpedia

    INDEX
    Explanations

    core concepts and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kabar
    0.52
     notícia
    0.51
     disfrutar
    0.50
     tourist
    0.49
     Businessman
    0.49
     pantai
    0.49
     airliner
    0.49
     swearing
    0.48
     berita
    0.48
     nạn
    0.48
    POSITIVE LOGITS
     schema
    0.91
     conceptually
    0.86
     syntactic
    0.79
     Schema
    0.78
     schemas
    0.77
     conceptual
    0.77
     defining
    0.76
     semantic
    0.76
    定義
    0.72
     abstract
    0.71
    Act Density 0.382%

    No Known Activations