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

    Neuronpedia

    INDEX
    Explanations

    further

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     некоторых
    -0.08
    она
    -0.08
     비롯
    -0.08
    Nano
    -0.08
     Viking
    -0.07
     трен
    -0.07
    Tou
    -0.07
     посредством
    -0.07
     проста
    -0.07
    aña
    -0.07
    POSITIVE LOGITS
     unexpl
    0.08
    isil
    0.08
     disclaim
    0.08
    詳
    0.08
    要求
    0.07
     complications
    0.07
     warranties
    0.07
     additional
    0.07
     much
    0.07
     witnesses
    0.07
    Act Density 0.010%

    No Known Activations