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

    Neuronpedia

    INDEX
    Explanations

    Memory addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _place
    -0.06
    ває
    -0.06
    unifu
    -0.06
     wired
    -0.06
     Out
    -0.06
     Bình
    -0.06
     Slave
    -0.06
    :UITableView
    -0.05
     Comb
    -0.05
     Swipe
    -0.05
    POSITIVE LOGITS
     AppConfig
    0.07
     国
    0.07
    يات
    0.07
    lanmıştır
    0.06
    (g
    0.06
    Ax
    0.06
     Eclipse
    0.06
    languages
    0.06
     çal
    0.06
     muster
    0.06
    Act Density 0.014%

    No Known Activations