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

    Neuronpedia

    INDEX
    Explanations

    Customer retention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    specs
    -0.07
     reg
    -0.07
     flat
    -0.06
     homogeneous
    -0.06
    commons
    -0.06
    есп
    -0.06
    Detail
    -0.06
    Linked
    -0.06
    (moment
    -0.06
    ighbour
    -0.06
    POSITIVE LOGITS
     ]}↵
    0.07
     hãy
    0.06
    /options
    0.06
     查询
    0.06
    λίου
    0.06
    /logo
    0.06
     enjo
    0.06
    .gs
    0.06
     analsex
    0.06
     ศ
    0.06
    Act Density 0.025%

    No Known Activations