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

    Neuronpedia

    INDEX
    Explanations

    Tag Archives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     немає
    -1.06
     pamph
    -0.96
    логии
    -0.96
     Adven
    -0.90
    自杀
    -0.90
    是指
    -0.89
    olymers
    -0.88
     tenda
    -0.87
    讲述
    -0.85
    ン
    -0.85
    POSITIVE LOGITS
    ger
    1.38
    ging
    1.30
     hanno
    1.30
     Tag
    1.23
    Tag
    1.17
    gings
    1.14
     tagging
    1.13
    gers
    1.13
    section
    1.05
    ématique
    1.03
    Act Density 0.023%

    No Known Activations