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

    Neuronpedia

    INDEX
    Explanations

    Quotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幸
    -0.07
     proof
    -0.07
    .station
    -0.07
     star
    -0.07
     стратег
    -0.06
     disadvantages
    -0.06
     ETF
    -0.06
    点
    -0.06
     ตาม
    -0.06
     百
    -0.06
    POSITIVE LOGITS
     dispenser
    0.07
     Desmond
    0.06
     Walton
    0.06
     turbulent
    0.06
     Osama
    0.06
     Dra
    0.06
    .ByteArray
    0.06
    ісля
    0.06
     náklady
    0.06
    خرى
    0.06
    Act Density 0.023%

    No Known Activations