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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Confederate
    -0.07
     люб
    -0.06
     jury
    -0.06
     pointers
    -0.06
    -down
    -0.06
     Jews
    -0.06
    Destructor
    -0.06
    Buttons
    -0.06
     tiny
    -0.06
    ее
    -0.06
    POSITIVE LOGITS
    字幕
    0.07
    укт
    0.07
    Ơ
    0.07
    роп
    0.06
    -san
    0.06
     الداخ
    0.06
    ‌ها
    0.06
    ?("
    0.06
    /{{
    0.06
    ơ
    0.06
    Act Density 0.032%

    No Known Activations