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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Traverse
    -0.07
     đị
    -0.07
    coupon
    -0.07
     لكن
    -0.06
     montage
    -0.06
     fiery
    -0.06
    การพ
    -0.06
     McMaster
    -0.06
     tiết
    -0.06
    Chance
    -0.06
    POSITIVE LOGITS
    録
    0.07
    /header
    0.07
    Received
    0.07
     Од
    0.06
    olicitud
    0.06
    .POST
    0.06
     відбува
    0.06
     Dimensions
    0.06
    姓名
    0.06
    <Response
    0.06
    Act Density 0.040%

    No Known Activations