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

    Neuronpedia

    INDEX
    Explanations

    Formal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     않았
    -0.07
    стра
    -0.06
     Вели
    -0.06
     eigentlich
    -0.06
    Nova
    -0.06
     atd
    -0.06
    Ru
    -0.06
     EventHandler
    -0.06
    央
    -0.06
    込み
    -0.06
    POSITIVE LOGITS
    Support
    0.07
    UME
    0.07
     MAIL
    0.07
    ussia
    0.07
     link
    0.07
    _account
    0.07
     makeover
    0.07
    DP
    0.07
    irk
    0.06
     stadium
    0.06
    Act Density 0.360%

    No Known Activations