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

    Neuronpedia

    INDEX
    Explanations

    Ben

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    api
    -0.08
    ӡ
    -0.08
    nest
    -0.08
    arty
    -0.07
    Tax
    -0.07
    纠纷
    -0.07
     qq
    -0.07
    -lines
    -0.07
    还记得
    -0.07
     fotos
    -0.07
    POSITIVE LOGITS
     CE
    0.08
     adversaries
    0.07
    Kim
    0.07
     Piece
    0.07
    ypad
    0.07
    .dictionary
    0.07
    remote
    0.07
    宫廷
    0.06
    들이
    0.06
     Jeremy
    0.06
    Act Density 0.004%

    No Known Activations