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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ptype
    -0.07
     When
    -0.07
    giatan
    -0.06
    説明
    -0.06
    ордин
    -0.06
    SERVICE
    -0.06
    уму
    -0.06
    ้อย
    -0.06
    EndTime
    -0.06
    .friend
    -0.06
    POSITIVE LOGITS
    {-
    0.07
    ')}}"></
    0.06
    -static
    0.06
    .TRA
    0.06
     breakpoints
    0.06
     armed
    0.06
    Bonus
    0.06
     Venture
    0.06
    (points
    0.06
    .Check
    0.06
    Act Density 0.022%

    No Known Activations