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

    Neuronpedia

    INDEX
    Explanations

    code operations and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంచరీలు
    0.26
     jūs
    0.26
     аўтаматы
    0.25
    ๙
    0.23
    ianthus
    0.23
    getBlueTeam
    0.23
    ८
    0.23
    setVelocity
    0.23
    .«
    0.23
    нь
    0.23
    POSITIVE LOGITS
     passed
    0.33
     remaining
    0.33
     metadata
    0.32
     initial
    0.31
     the
    0.31
     main
    0.31
     dataframe
    0.31
     internal
    0.31
     user
    0.30
     calculate
    0.30
    Act Density 0.366%

    No Known Activations