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

    Neuronpedia

    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bijge
    -0.08
    -0.08
    机器人
    -0.08
     computadores
    -0.07
    筛
    -0.07
     объектив
    -0.07
    通信
    -0.07
     exquis
    -0.07
     irresistible
    -0.07
    指导
    -0.07
    POSITIVE LOGITS
     রাখা
    0.10
     bearish
    0.10
     holdings
    0.10
     pendiente
    0.09
    signed
    0.09
     management
    0.09
     Holdings
    0.09
     удерж
    0.09
    kx
    0.09
     pendientes
    0.08
    Act Density 0.005%
    No Known Activations