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

    Neuronpedia

    INDEX
    Explanations

    explanation of improvements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    某些
    0.74
     혹은
    0.74
    Certain
    0.65
    Strategies
    0.64
    Partners
    0.63
     किंवा
    0.63
    петров
    0.63
    หรือ
    0.62
    Some
    0.61
    ContentTypes
    0.61
    POSITIVE LOGITS
     updated
    0.86
     argument
    0.81
     аргу
    0.77
     removes
    0.75
     use
    0.75
     formatting
    0.74
     utiliser
    0.73
     saves
    0.72
     added
    0.71
     inclui
    0.71
    Act Density 0.003%

    No Known Activations