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

    Neuronpedia

    INDEX
    Explanations

    list names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wilkinson
    0.79
     Hawkins
    0.76
     সিলেট
    0.75
    HNO
    0.74
    ഃ
    0.72
     পৌছ
    0.71
     cacao
    0.71
    பிலோ
    0.71
     Victims
    0.71
    国際
    0.70
    POSITIVE LOGITS
     Fall
    0.72
     fall
    0.71
     అనే
    0.65
     falls
    0.64
    ளர்
    0.63
     Narrow
    0.62
     jsem
    0.62
     EV
    0.61
    庵
    0.60
     apartment
    0.59
    Act Density 0.253%

    No Known Activations