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

    Neuronpedia

    INDEX
    Explanations

    money

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     requires
    -0.06
     статьи
    -0.06
     famous
    -0.06
     activated
    -0.06
     capped
    -0.06
    advance
    -0.06
     accountable
    -0.06
     выступ
    -0.06
    Values
    -0.06
     تقو
    -0.05
    POSITIVE LOGITS
    =$((
    0.08
    .Matrix
    0.07
    edik
    0.07
    ATFORM
    0.07
     slept
    0.06
    砲
    0.06
     exce
    0.06
    _low
    0.06
     Sofa
    0.06
    .CommandType
    0.06
    Act Density 0.018%

    No Known Activations