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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    會在
    0.53
     университета
    0.51
     કંપની
    0.50
     पढ़ेंगे
    0.50
    식을
    0.47
    ница
    0.47
     सीखेंगे
    0.47
    技术的
    0.47
    Дру
    0.46
    बरोबर
    0.46
    POSITIVE LOGITS
     influx
    0.47
     lu
    0.45
     contact
    0.44
     reach
    0.44
     reward
    0.43
     flyer
    0.43
     relic
    0.42
     incoming
    0.42
     faint
    0.41
     loin
    0.41
    Act Density 0.006%

    No Known Activations