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

    Neuronpedia

    INDEX
    Explanations

    goes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大理
    -0.07
    🐆
    -0.07
     nackte
    -0.07
     completamente
    -0.06
    前瞻
    -0.06
     deps
    -0.06
     mãe
    -0.06
    硼
    -0.06
     страниц
    -0.06
    _INTERNAL
    -0.06
    POSITIVE LOGITS
     may
    0.07
     Would
    0.07
    か
    0.07
     Peripheral
    0.07
     Will
    0.06
     театр
    0.06
     Monthly
    0.06
    TM
    0.06
    Order
    0.06
    称
    0.06
    Act Density 0.002%

    No Known Activations