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

    Neuronpedia

    INDEX
    Explanations

    erotica

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rum
    -0.08
    草莓
    -0.07
    .reset
    -0.07
     thông
    -0.07
    index
    -0.07
    	url
    -0.07
     AG
    -0.07
     Shelter
    -0.07
     widespread
    -0.07
     album
    -0.07
    POSITIVE LOGITS
    ва
    0.08
    ┓
    0.07
    #
    0.07
    贽
    0.07
    ϡ
    0.07
     HCI
    0.07
     fgets
    0.07
    机遇
    0.07
    .Dot
    0.07
    QE
    0.07
    Act Density 0.002%

    No Known Activations