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

    Neuronpedia

    INDEX
    Explanations

    across

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вну
    -0.07
    _fitness
    -0.07
     Loot
    -0.07
    .ut
    -0.06
    sit
    -0.06
    ACKET
    -0.06
    setOnClickListener
    -0.06
     initData
    -0.06
    ыт
    -0.06
    eut
    -0.06
    POSITIVE LOGITS
     across
    0.07
    mailbox
    0.06
     newcomer
    0.06
    홀
    0.06
     arises
    0.06
    ียว
    0.06
    //↵
    0.06
     handic
    0.06
     celestial
    0.06
     upon
    0.06
    Act Density 0.003%

    No Known Activations